Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/UFO

UFO

Reported on 250 benchmarks across 9 tasks · 1 paper · 215 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology136 results

3DonCoSOD3k
S-measure· 2022-03-09
0.819
best: 0.851 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonCoSOD3k
max E-measure· 2022-03-09
0.874
best: 0.901 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonCoSOD3k
max F-measure· 2022-03-09
0.797
best: 0.835 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonCoSOD3k
mean F-measure· 2022-03-09
0.783
best: 0.815 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DoniCoSeg
MAE· 2022-03-09
0.029
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DoniCoSeg
S-measure· 2022-03-09
0.924
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DoniCoSeg
max E-measure· 2022-03-09
0.969
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DoniCoSeg
max F-measure· 2022-03-09
0.953
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonCoCA
MAE· 2022-03-09
0.095
best: 0.081 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonCoCA
Mean F-measure· 2022-03-09
0.555
best: 0.612 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonCoCA
S-measure· 2022-03-09
0.697
best: 0.738 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonCoCA
max E-measure· 2022-03-09
0.782
best: 0.814 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonCoCA
max F-measure· 2022-03-09
0.571
best: 0.637 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonCoCA
mean E-measure· 2022-03-09
0.762
best: 0.783 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonCoSal2015
max F-measure· 2022-03-09
0.865
best: 0.905 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonCoSal2015
mean E-measure· 2022-03-09
0.889
best: 0.922 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonCoSal2015
mean F-measure· 2022-03-09
0.848
best: 0.883 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonFBMS-59
AVERAGE MAE· 2022-03-09
0.028
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonFBMS-59
MAX F-MEASURE· 2022-03-09
0.89
best: 0.906 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonFBMS-59
S-Measure· 2022-03-09
0.894
best: 0.926 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonSegTrack v2
AVERAGE MAE· uses extra data· 2022-03-09
0.022
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonSegTrack v2
MAX F-MEASURE· uses extra data· 2022-03-09
0.863
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonSegTrack v2
S-Measure· uses extra data· 2022-03-09
0.892
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonDAVIS-2016
AVERAGE MAE· uses extra data· 2022-03-09
0.015
best: 0.01 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonDAVIS-2016
MAX F-MEASURE· uses extra data· 2022-03-09
0.906
best: 0.939 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonDAVIS-2016
S-Measure· uses extra data· 2022-03-09
0.918
best: 0.945 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonViSal
Average MAE· 2022-03-09
0.011
best: 0.01 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonViSal
S-Measure· 2022-03-09
0.953
best: 0.962 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonViSal
max E-measure· 2022-03-09
0.987
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonCoSOD3k
S-measure· 2022-03-09
0.819
best: 0.851 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonCoSOD3k
max E-measure· 2022-03-09
0.874
best: 0.901 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonCoSOD3k
max F-measure· 2022-03-09
0.797
best: 0.835 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonCoSOD3k
mean F-measure· 2022-03-09
0.783
best: 0.815 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationoniCoSeg
MAE· 2022-03-09
0.029
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationoniCoSeg
S-measure· 2022-03-09
0.924
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationoniCoSeg
max E-measure· 2022-03-09
0.969
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationoniCoSeg
max F-measure· 2022-03-09
0.953
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonCoCA
MAE· 2022-03-09
0.095
best: 0.081 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonCoCA
Mean F-measure· 2022-03-09
0.555
best: 0.612 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonCoCA
S-measure· 2022-03-09
0.697
best: 0.738 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonCoCA
max E-measure· 2022-03-09
0.782
best: 0.814 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonCoCA
max F-measure· 2022-03-09
0.571
best: 0.637 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonCoCA
mean E-measure· 2022-03-09
0.762
best: 0.783 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonCoSal2015
max F-measure· 2022-03-09
0.865
best: 0.905 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonCoSal2015
mean E-measure· 2022-03-09
0.889
best: 0.922 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonCoSal2015
mean F-measure· 2022-03-09
0.848
best: 0.883 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonFBMS-59
AVERAGE MAE· 2022-03-09
0.028
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonFBMS-59
MAX F-MEASURE· 2022-03-09
0.89
best: 0.906 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonFBMS-59
S-Measure· 2022-03-09
0.894
best: 0.926 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonSegTrack v2
AVERAGE MAE· uses extra data· 2022-03-09
0.022
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonSegTrack v2
MAX F-MEASURE· uses extra data· 2022-03-09
0.863
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonSegTrack v2
S-Measure· uses extra data· 2022-03-09
0.892
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonDAVIS-2016
AVERAGE MAE· uses extra data· 2022-03-09
0.015
best: 0.01 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonDAVIS-2016
MAX F-MEASURE· uses extra data· 2022-03-09
0.906
best: 0.939 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonDAVIS-2016
S-Measure· uses extra data· 2022-03-09
0.918
best: 0.945 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonViSal
Average MAE· 2022-03-09
0.011
best: 0.01 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonViSal
S-Measure· 2022-03-09
0.953
best: 0.962 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonViSal
max E-measure· 2022-03-09
0.987
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononCoSOD3k
S-measure· 2022-03-09
0.819
best: 0.851 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononCoSOD3k
max E-measure· 2022-03-09
0.874
best: 0.901 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononCoSOD3k
max F-measure· 2022-03-09
0.797
best: 0.835 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononCoSOD3k
mean F-measure· 2022-03-09
0.783
best: 0.815 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononiCoSeg
MAE· 2022-03-09
0.029
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononiCoSeg
S-measure· 2022-03-09
0.924
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononiCoSeg
max E-measure· 2022-03-09
0.969
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononiCoSeg
max F-measure· 2022-03-09
0.953
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononCoCA
MAE· 2022-03-09
0.095
best: 0.081 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononCoCA
Mean F-measure· 2022-03-09
0.555
best: 0.612 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononCoCA
S-measure· 2022-03-09
0.697
best: 0.738 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononCoCA
max E-measure· 2022-03-09
0.782
best: 0.814 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononCoCA
max F-measure· 2022-03-09
0.571
best: 0.637 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononCoCA
mean E-measure· 2022-03-09
0.762
best: 0.783 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononCoSal2015
max F-measure· 2022-03-09
0.865
best: 0.905 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononCoSal2015
mean E-measure· 2022-03-09
0.889
best: 0.922 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononCoSal2015
mean F-measure· 2022-03-09
0.848
best: 0.883 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononFBMS-59
AVERAGE MAE· 2022-03-09
0.028
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononFBMS-59
MAX F-MEASURE· 2022-03-09
0.89
best: 0.906 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononFBMS-59
S-Measure· 2022-03-09
0.894
best: 0.926 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononSegTrack v2
AVERAGE MAE· uses extra data· 2022-03-09
0.022
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononSegTrack v2
MAX F-MEASURE· uses extra data· 2022-03-09
0.863
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononSegTrack v2
S-Measure· uses extra data· 2022-03-09
0.892
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononDAVIS-2016
AVERAGE MAE· uses extra data· 2022-03-09
0.015
best: 0.01 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononDAVIS-2016
MAX F-MEASURE· uses extra data· 2022-03-09
0.906
best: 0.939 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononDAVIS-2016
S-Measure· uses extra data· 2022-03-09
0.918
best: 0.945 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononViSal
Average MAE· 2022-03-09
0.011
best: 0.01 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononViSal
S-Measure· 2022-03-09
0.953
best: 0.962 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononViSal
max E-measure· 2022-03-09
0.987
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konCoSOD3k
S-measure· 2022-03-09
0.819
best: 0.851 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konCoSOD3k
max E-measure· 2022-03-09
0.874
best: 0.901 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konCoSOD3k
max F-measure· 2022-03-09
0.797
best: 0.835 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konCoSOD3k
mean F-measure· 2022-03-09
0.783
best: 0.815 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16koniCoSeg
MAE· 2022-03-09
0.029
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16koniCoSeg
S-measure· 2022-03-09
0.924
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16koniCoSeg
max E-measure· 2022-03-09
0.969
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16koniCoSeg
max F-measure· 2022-03-09
0.953
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konCoCA
MAE· 2022-03-09
0.095
best: 0.081 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konCoCA
Mean F-measure· 2022-03-09
0.555
best: 0.612 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konCoCA
S-measure· 2022-03-09
0.697
best: 0.738 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konCoCA
max E-measure· 2022-03-09
0.782
best: 0.814 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konCoCA
max F-measure· 2022-03-09
0.571
best: 0.637 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konCoCA
mean E-measure· 2022-03-09
0.762
best: 0.783 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konCoSal2015
max F-measure· 2022-03-09
0.865
best: 0.905 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konCoSal2015
mean E-measure· 2022-03-09
0.889
best: 0.922 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konCoSal2015
mean F-measure· 2022-03-09
0.848
best: 0.883 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konFBMS-59
AVERAGE MAE· 2022-03-09
0.028
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konFBMS-59
MAX F-MEASURE· 2022-03-09
0.89
best: 0.906 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konFBMS-59
S-Measure· 2022-03-09
0.894
best: 0.926 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konSegTrack v2
AVERAGE MAE· uses extra data· 2022-03-09
0.022
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konSegTrack v2
MAX F-MEASURE· uses extra data· 2022-03-09
0.863
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konSegTrack v2
S-Measure· uses extra data· 2022-03-09
0.892
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konDAVIS-2016
AVERAGE MAE· uses extra data· 2022-03-09
0.015
best: 0.01 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konDAVIS-2016
MAX F-MEASURE· uses extra data· 2022-03-09
0.906
best: 0.939 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konDAVIS-2016
S-Measure· uses extra data· 2022-03-09
0.918
best: 0.945 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konViSal
Average MAE· 2022-03-09
0.011
best: 0.01 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konViSal
S-Measure· 2022-03-09
0.953
best: 0.962 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konViSal
max E-measure· 2022-03-09
0.987
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonCoSOD3k
MAE· 2022-03-09
0.073
best: 0.062 (GCoNet+)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonCoSOD3k
mean E-measure· 2022-03-09
0.855
best: 0.881 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonCoSal2015
MAE· 2022-03-09
0.064
best: 0.045 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonCoSal2015
S-measure· 2022-03-09
0.86
best: 0.897 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
3DonCoSal2015
max E-measure· 2022-03-09
0.906
best: 0.936 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonCoSOD3k
MAE· 2022-03-09
0.073
best: 0.062 (GCoNet+)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonCoSOD3k
mean E-measure· 2022-03-09
0.855
best: 0.881 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonCoSal2015
MAE· 2022-03-09
0.064
best: 0.045 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonCoSal2015
S-measure· 2022-03-09
0.86
best: 0.897 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D ClassificationonCoSal2015
max E-measure· 2022-03-09
0.906
best: 0.936 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononCoSOD3k
MAE· 2022-03-09
0.073
best: 0.062 (GCoNet+)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononCoSOD3k
mean E-measure· 2022-03-09
0.855
best: 0.881 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononCoSal2015
MAE· 2022-03-09
0.064
best: 0.045 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononCoSal2015
S-measure· 2022-03-09
0.86
best: 0.897 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
2D Object DetectiononCoSal2015
max E-measure· 2022-03-09
0.906
best: 0.936 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konCoSOD3k
MAE· 2022-03-09
0.073
best: 0.062 (GCoNet+)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konCoSOD3k
mean E-measure· 2022-03-09
0.855
best: 0.881 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konCoSal2015
MAE· 2022-03-09
0.064
best: 0.045 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konCoSal2015
S-measure· 2022-03-09
0.86
best: 0.897 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
16konCoSal2015
max E-measure· 2022-03-09
0.906
best: 0.936 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708

Computer Vision114 results

VideoonFBMS-59
AVERAGE MAE· 2022-03-09
0.028
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
VideoonFBMS-59
MAX F-MEASURE· 2022-03-09
0.89
best: 0.906 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
VideoonFBMS-59
S-Measure· 2022-03-09
0.894
best: 0.926 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
VideoonSegTrack v2
AVERAGE MAE· uses extra data· 2022-03-09
0.022
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
VideoonSegTrack v2
MAX F-MEASURE· uses extra data· 2022-03-09
0.863
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
VideoonSegTrack v2
S-Measure· uses extra data· 2022-03-09
0.892
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
VideoonDAVIS-2016
AVERAGE MAE· uses extra data· 2022-03-09
0.015
best: 0.01 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
VideoonDAVIS-2016
MAX F-MEASURE· uses extra data· 2022-03-09
0.906
best: 0.939 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
VideoonDAVIS-2016
S-Measure· uses extra data· 2022-03-09
0.918
best: 0.945 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
VideoonViSal
Average MAE· 2022-03-09
0.011
best: 0.01 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
VideoonViSal
S-Measure· 2022-03-09
0.953
best: 0.962 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
VideoonViSal
max E-measure· 2022-03-09
0.987
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Saliency DetectiononCoSOD3k
S-measure· 2022-03-09
0.819
best: 0.851 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Saliency DetectiononCoSOD3k
max E-measure· 2022-03-09
0.874
best: 0.901 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Saliency DetectiononCoSOD3k
max F-measure· 2022-03-09
0.797
best: 0.835 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Saliency DetectiononCoSOD3k
mean F-measure· 2022-03-09
0.783
best: 0.815 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Saliency DetectiononiCoSeg
MAE· 2022-03-09
0.029
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Saliency DetectiononiCoSeg
S-measure· 2022-03-09
0.924
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Saliency DetectiononiCoSeg
max E-measure· 2022-03-09
0.969
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Saliency DetectiononiCoSeg
max F-measure· 2022-03-09
0.953
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Saliency DetectiononCoCA
MAE· 2022-03-09
0.095
best: 0.081 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Saliency DetectiononCoCA
Mean F-measure· 2022-03-09
0.555
best: 0.612 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Saliency DetectiononCoCA
S-measure· 2022-03-09
0.697
best: 0.738 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Saliency DetectiononCoCA
max E-measure· 2022-03-09
0.782
best: 0.814 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Saliency DetectiononCoCA
max F-measure· 2022-03-09
0.571
best: 0.637 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Saliency DetectiononCoCA
mean E-measure· 2022-03-09
0.762
best: 0.783 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Saliency DetectiononCoSal2015
max F-measure· 2022-03-09
0.865
best: 0.905 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Saliency DetectiononCoSal2015
mean E-measure· 2022-03-09
0.889
best: 0.922 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Saliency DetectiononCoSal2015
mean F-measure· 2022-03-09
0.848
best: 0.883 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononCoSOD3k
S-measure· 2022-03-09
0.819
best: 0.851 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononCoSOD3k
max E-measure· 2022-03-09
0.874
best: 0.901 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononCoSOD3k
max F-measure· 2022-03-09
0.797
best: 0.835 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononCoSOD3k
mean F-measure· 2022-03-09
0.783
best: 0.815 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononiCoSeg
MAE· 2022-03-09
0.029
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononiCoSeg
S-measure· 2022-03-09
0.924
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononiCoSeg
max E-measure· 2022-03-09
0.969
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononiCoSeg
max F-measure· 2022-03-09
0.953
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononCoCA
MAE· 2022-03-09
0.095
best: 0.081 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononCoCA
Mean F-measure· 2022-03-09
0.555
best: 0.612 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononCoCA
S-measure· 2022-03-09
0.697
best: 0.738 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononCoCA
max E-measure· 2022-03-09
0.782
best: 0.814 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononCoCA
max F-measure· 2022-03-09
0.571
best: 0.637 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononCoCA
mean E-measure· 2022-03-09
0.762
best: 0.783 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononCoSal2015
max F-measure· 2022-03-09
0.865
best: 0.905 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononCoSal2015
mean E-measure· 2022-03-09
0.889
best: 0.922 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononCoSal2015
mean F-measure· 2022-03-09
0.848
best: 0.883 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononFBMS-59
AVERAGE MAE· 2022-03-09
0.028
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononFBMS-59
MAX F-MEASURE· 2022-03-09
0.89
best: 0.906 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononFBMS-59
S-Measure· 2022-03-09
0.894
best: 0.926 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononSegTrack v2
AVERAGE MAE· uses extra data· 2022-03-09
0.022
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononSegTrack v2
MAX F-MEASURE· uses extra data· 2022-03-09
0.863
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononSegTrack v2
S-Measure· uses extra data· 2022-03-09
0.892
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononDAVIS-2016
AVERAGE MAE· uses extra data· 2022-03-09
0.015
best: 0.01 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononDAVIS-2016
MAX F-MEASURE· uses extra data· 2022-03-09
0.906
best: 0.939 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononDAVIS-2016
S-Measure· uses extra data· 2022-03-09
0.918
best: 0.945 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononViSal
Average MAE· 2022-03-09
0.011
best: 0.01 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononViSal
S-Measure· 2022-03-09
0.953
best: 0.962 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononViSal
max E-measure· 2022-03-09
0.987
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Video Object SegmentationonFBMS-59
AVERAGE MAE· 2022-03-09
0.028
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Video Object SegmentationonFBMS-59
MAX F-MEASURE· 2022-03-09
0.89
best: 0.906 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Video Object SegmentationonFBMS-59
S-Measure· 2022-03-09
0.894
best: 0.926 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Video Object SegmentationonSegTrack v2
AVERAGE MAE· uses extra data· 2022-03-09
0.022
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Video Object SegmentationonSegTrack v2
MAX F-MEASURE· uses extra data· 2022-03-09
0.863
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Video Object SegmentationonSegTrack v2
S-Measure· uses extra data· 2022-03-09
0.892
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Video Object SegmentationonDAVIS-2016
AVERAGE MAE· uses extra data· 2022-03-09
0.015
best: 0.01 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Video Object SegmentationonDAVIS-2016
MAX F-MEASURE· uses extra data· 2022-03-09
0.906
best: 0.939 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Video Object SegmentationonDAVIS-2016
S-Measure· uses extra data· 2022-03-09
0.918
best: 0.945 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Video Object SegmentationonViSal
Average MAE· 2022-03-09
0.011
best: 0.01 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Video Object SegmentationonViSal
S-Measure· 2022-03-09
0.953
best: 0.962 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Video Object SegmentationonViSal
max E-measure· 2022-03-09
0.987
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononCoSOD3k
S-measure· 2022-03-09
0.819
best: 0.851 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononCoSOD3k
max E-measure· 2022-03-09
0.874
best: 0.901 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononCoSOD3k
max F-measure· 2022-03-09
0.797
best: 0.835 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononCoSOD3k
mean F-measure· 2022-03-09
0.783
best: 0.815 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononiCoSeg
MAE· 2022-03-09
0.029
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononiCoSeg
S-measure· 2022-03-09
0.924
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononiCoSeg
max E-measure· 2022-03-09
0.969
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononiCoSeg
max F-measure· 2022-03-09
0.953
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononCoCA
MAE· 2022-03-09
0.095
best: 0.081 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononCoCA
Mean F-measure· 2022-03-09
0.555
best: 0.612 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononCoCA
S-measure· 2022-03-09
0.697
best: 0.738 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononCoCA
max E-measure· 2022-03-09
0.782
best: 0.814 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononCoCA
max F-measure· 2022-03-09
0.571
best: 0.637 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononCoCA
mean E-measure· 2022-03-09
0.762
best: 0.783 (GCoNet+)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononCoSal2015
max F-measure· 2022-03-09
0.865
best: 0.905 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononCoSal2015
mean E-measure· 2022-03-09
0.889
best: 0.922 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononCoSal2015
mean F-measure· 2022-03-09
0.848
best: 0.883 (DMT)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononFBMS-59
AVERAGE MAE· 2022-03-09
0.028
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononFBMS-59
MAX F-MEASURE· 2022-03-09
0.89
best: 0.906 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononFBMS-59
S-Measure· 2022-03-09
0.894
best: 0.926 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononSegTrack v2
AVERAGE MAE· uses extra data· 2022-03-09
0.022
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononSegTrack v2
MAX F-MEASURE· uses extra data· 2022-03-09
0.863
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononSegTrack v2
S-Measure· uses extra data· 2022-03-09
0.892
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononDAVIS-2016
AVERAGE MAE· uses extra data· 2022-03-09
0.015
best: 0.01 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononDAVIS-2016
MAX F-MEASURE· uses extra data· 2022-03-09
0.906
best: 0.939 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononDAVIS-2016
S-Measure· uses extra data· 2022-03-09
0.918
best: 0.945 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononViSal
Average MAE· 2022-03-09
0.011
best: 0.01 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononViSal
S-Measure· 2022-03-09
0.953
best: 0.962 (RealFlow)
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononViSal
max E-measure· 2022-03-09
0.987
SOTA
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Saliency DetectiononCoSOD3k
MAE· 2022-03-09
0.073
best: 0.062 (GCoNet+)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Saliency DetectiononCoSOD3k
mean E-measure· 2022-03-09
0.855
best: 0.881 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Saliency DetectiononCoSal2015
MAE· 2022-03-09
0.064
best: 0.045 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Saliency DetectiononCoSal2015
S-measure· 2022-03-09
0.86
best: 0.897 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Saliency DetectiononCoSal2015
max E-measure· 2022-03-09
0.906
best: 0.936 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononCoSOD3k
MAE· 2022-03-09
0.073
best: 0.062 (GCoNet+)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononCoSOD3k
mean E-measure· 2022-03-09
0.855
best: 0.881 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononCoSal2015
MAE· 2022-03-09
0.064
best: 0.045 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononCoSal2015
S-measure· 2022-03-09
0.86
best: 0.897 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
Object DetectiononCoSal2015
max E-measure· 2022-03-09
0.906
best: 0.936 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononCoSOD3k
MAE· 2022-03-09
0.073
best: 0.062 (GCoNet+)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononCoSOD3k
mean E-measure· 2022-03-09
0.855
best: 0.881 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononCoSal2015
MAE· 2022-03-09
0.064
best: 0.045 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononCoSal2015
S-measure· 2022-03-09
0.86
best: 0.897 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708
RGB Salient Object DetectiononCoSal2015
max E-measure· 2022-03-09
0.906
best: 0.936 (DMT)
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection arXiv:2203.04708