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/VST

VST

Reported on 34 benchmarks across 8 tasks · 1 paper · 20 SOTA

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

Methodology25 results

3DonSIP
Average MAE· 2021-04-25
0.04
best: 0.032 (DFormer-L)
SOTA
Visual Saliency Transformer arXiv:2104.12099
3DonSIP
S-Measure· 2021-04-25
90.4
best: 91.5 (DFormer-L)
SOTA
Visual Saliency Transformer arXiv:2104.12099
3DonSIP
max F-Measure· 2021-04-25
91.5
best: 93.8 (DFormer-L)
SOTA
Visual Saliency Transformer arXiv:2104.12099
3DonNJUD
S-Measure· 2021-04-25
0.922
SOTA
Visual Saliency Transformer arXiv:2104.12099
2D ClassificationonSIP
Average MAE· 2021-04-25
0.04
best: 0.032 (DFormer-L)
SOTA
Visual Saliency Transformer arXiv:2104.12099
2D ClassificationonSIP
S-Measure· 2021-04-25
90.4
best: 91.5 (DFormer-L)
SOTA
Visual Saliency Transformer arXiv:2104.12099
2D ClassificationonSIP
max F-Measure· 2021-04-25
91.5
best: 93.8 (DFormer-L)
SOTA
Visual Saliency Transformer arXiv:2104.12099
2D ClassificationonNJUD
S-Measure· 2021-04-25
0.922
SOTA
Visual Saliency Transformer arXiv:2104.12099
2D Object DetectiononSIP
Average MAE· 2021-04-25
0.04
best: 0.032 (DFormer-L)
SOTA
Visual Saliency Transformer arXiv:2104.12099
2D Object DetectiononSIP
S-Measure· 2021-04-25
90.4
best: 91.5 (DFormer-L)
SOTA
Visual Saliency Transformer arXiv:2104.12099
2D Object DetectiononSIP
max F-Measure· 2021-04-25
91.5
best: 93.8 (DFormer-L)
SOTA
Visual Saliency Transformer arXiv:2104.12099
2D Object DetectiononNJUD
S-Measure· 2021-04-25
0.922
SOTA
Visual Saliency Transformer arXiv:2104.12099
16konSIP
Average MAE· 2021-04-25
0.04
best: 0.032 (DFormer-L)
SOTA
Visual Saliency Transformer arXiv:2104.12099
16konSIP
S-Measure· 2021-04-25
90.4
best: 91.5 (DFormer-L)
SOTA
Visual Saliency Transformer arXiv:2104.12099
16konSIP
max F-Measure· 2021-04-25
91.5
best: 93.8 (DFormer-L)
SOTA
Visual Saliency Transformer arXiv:2104.12099
16konNJUD
S-Measure· 2021-04-25
0.922
SOTA
Visual Saliency Transformer arXiv:2104.12099
3DonSIP
max E-Measure· 2021-04-25
94.4
best: 95 (DFormer-L)
Visual Saliency Transformer arXiv:2104.12099
3DonNLPR
S-Measure· 2021-04-25
0.932
best: 94.2 (DFormer-L)
Visual Saliency Transformer arXiv:2104.12099
2D ClassificationonSIP
max E-Measure· 2021-04-25
94.4
best: 95 (DFormer-L)
Visual Saliency Transformer arXiv:2104.12099
2D ClassificationonNLPR
S-Measure· 2021-04-25
0.932
best: 94.2 (DFormer-L)
Visual Saliency Transformer arXiv:2104.12099
2D Object DetectiononSIP
max E-Measure· 2021-04-25
94.4
best: 95 (DFormer-L)
Visual Saliency Transformer arXiv:2104.12099
2D Object DetectiononNLPR
S-Measure· 2021-04-25
0.932
best: 94.2 (DFormer-L)
Visual Saliency Transformer arXiv:2104.12099
2D Object DetectiononRGB-T-Glass-Segmentation
MAE· 2021-04-25
0.044
best: 0.024 (RGB-T-Glass-Segmentation)
Visual Saliency Transformer arXiv:2104.12099
16konSIP
max E-Measure· 2021-04-25
94.4
best: 95 (DFormer-L)
Visual Saliency Transformer arXiv:2104.12099
16konNLPR
S-Measure· 2021-04-25
0.932
best: 94.2 (DFormer-L)
Visual Saliency Transformer arXiv:2104.12099

Computer Vision7 results

Object DetectiononSIP
Average MAE· 2021-04-25
0.04
best: 0.032 (DFormer-L)
SOTA
Visual Saliency Transformer arXiv:2104.12099
Object DetectiononSIP
S-Measure· 2021-04-25
90.4
best: 91.5 (DFormer-L)
SOTA
Visual Saliency Transformer arXiv:2104.12099
Object DetectiononSIP
max F-Measure· 2021-04-25
91.5
best: 93.8 (DFormer-L)
SOTA
Visual Saliency Transformer arXiv:2104.12099
Object DetectiononNJUD
S-Measure· 2021-04-25
0.922
SOTA
Visual Saliency Transformer arXiv:2104.12099
Object DetectiononSIP
max E-Measure· 2021-04-25
94.4
best: 95 (DFormer-L)
Visual Saliency Transformer arXiv:2104.12099
Object DetectiononNLPR
S-Measure· 2021-04-25
0.932
best: 94.2 (DFormer-L)
Visual Saliency Transformer arXiv:2104.12099
Scene SegmentationonRGB-T-Glass-Segmentation
MAE· 2021-04-25
0.044
best: 0.024 (RGB-T-Glass-Segmentation)
Visual Saliency Transformer arXiv:2104.12099

Medical1 result

Semantic SegmentationonRGB-T-Glass-Segmentation
MAE· 2021-04-25
0.044
best: 0.024 (RGB-T-Glass-Segmentation)
Visual Saliency Transformer arXiv:2104.12099

Audio1 result

10-shot image generationonRGB-T-Glass-Segmentation
MAE· 2021-04-25
0.044
best: 0.024 (RGB-T-Glass-Segmentation)
Visual Saliency Transformer arXiv:2104.12099