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/CFBI+

CFBI+

Reported on 67 benchmarks across 3 tasks · 3 papers · 51 SOTA

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

Computer Vision75 results

VideoonYouTube-VOS 2019
Jaccard (Unseen)· 2020-10-13
77.1
best: 754.8 (R50-AOST (L'=1))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonYouTube-VOS 2018
F-Measure (Seen)· 2020-10-13
86.6
best: 91 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonYouTube-VOS 2018
F-Measure (Unseen)· 2020-10-13
85.6
best: 90.2 (XMem (BL30K, MS))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonYouTube-VOS 2018
Jaccard (Seen)· 2020-10-13
81.8
best: 86.6 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonYouTube-VOS 2018
Jaccard (Unseen)· 2020-10-13
77.1
best: 82.2 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonYouTube-VOS 2018
Mean Jaccard & F-Measure· 2020-10-13
82.8
best: 86.9 (XMem (BL30K, MS))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonDAVIS 2017 (val)
F-measure· 2020-10-13
85.7
best: 92.6 (XMem (BLK30K, MS))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonDAVIS 2017 (val)
Jaccard· 2020-10-13
80.1
best: 86.3 (XMem (BLK30K, MS))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonDAVIS 2017 (val)
Mean Jaccard & F-Measure· 2020-10-13
82.9
best: 89.5 (XMem (BLK30K, MS))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonDAVIS 2017 (val)
F-measure (Mean)· 2020-10-13
85.7
best: 93.4 (Cutie+ (base))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonDAVIS 2017 (val)
J&F· 2020-10-13
82.9
best: 90.7 (SAM2)
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonDAVIS 2017 (val)
Jaccard (Mean)· 2020-10-13
80.1
best: 87.5 (Cutie+ (base))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonDAVIS 2017 (test-dev)
F-measure (Mean)· 2020-10-13
81.6
best: 91.4 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonDAVIS 2017 (test-dev)
J&F· 2020-10-13
78
best: 88.1 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonDAVIS 2017 (test-dev)
Jaccard (Mean)· 2020-10-13
74.4
best: 84.7 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonYouTube-VOS 2018
Overall· 2020-10-13
82.8
best: 87.5 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonYouTube-VOS 2019
Jaccard (Unseen)· 2020-10-13
77.1
best: 754.8 (R50-AOST (L'=1))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonYouTube-VOS 2018
F-Measure (Seen)· 2020-10-13
86.6
best: 91 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonYouTube-VOS 2018
F-Measure (Unseen)· 2020-10-13
85.6
best: 90.2 (XMem (BL30K, MS))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonYouTube-VOS 2018
Jaccard (Seen)· 2020-10-13
81.8
best: 86.6 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonYouTube-VOS 2018
Jaccard (Unseen)· 2020-10-13
77.1
best: 82.2 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonYouTube-VOS 2018
Mean Jaccard & F-Measure· 2020-10-13
82.8
best: 86.9 (XMem (BL30K, MS))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonDAVIS 2017 (val)
F-measure· 2020-10-13
85.7
best: 92.6 (XMem (BLK30K, MS))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonDAVIS 2017 (val)
Jaccard· 2020-10-13
80.1
best: 86.3 (XMem (BLK30K, MS))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonDAVIS 2017 (val)
Mean Jaccard & F-Measure· 2020-10-13
82.9
best: 89.5 (XMem (BLK30K, MS))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonDAVIS 2017 (val)
F-measure (Mean)· 2020-10-13
85.7
best: 93.4 (Cutie+ (base))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonDAVIS 2017 (val)
J&F· 2020-10-13
82.9
best: 90.7 (SAM2)
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonDAVIS 2017 (val)
Jaccard (Mean)· 2020-10-13
80.1
best: 87.5 (Cutie+ (base))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonDAVIS 2017 (test-dev)
F-measure (Mean)· 2020-10-13
81.6
best: 91.4 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonDAVIS 2017 (test-dev)
J&F· 2020-10-13
78
best: 88.1 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonDAVIS 2017 (test-dev)
Jaccard (Mean)· 2020-10-13
74.4
best: 84.7 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonYouTube-VOS 2018
Overall· 2020-10-13
82.8
best: 87.5 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
F-measure (Mean)· 2020-10-13
85.7
best: 93.4 (Cutie+ (base))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
J&F· 2020-10-13
82.9
best: 90.7 (SAM2)
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
Jaccard (Mean)· 2020-10-13
80.1
best: 87.5 (Cutie+ (base))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
F-measure (Mean)· 2020-10-13
81.6
best: 91.4 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
J&F· 2020-10-13
78
best: 88.1 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
Jaccard (Mean)· 2020-10-13
74.4
best: 84.7 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Semi-Supervised Video Object SegmentationonYouTube-VOS 2018
F-Measure (Seen)· 2020-10-13
86.6
best: 91 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Semi-Supervised Video Object SegmentationonYouTube-VOS 2018
F-Measure (Unseen)· 2020-10-13
85.6
best: 90.2 (XMem (BL30K, MS))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Semi-Supervised Video Object SegmentationonYouTube-VOS 2018
Jaccard (Seen)· 2020-10-13
81.8
best: 86.6 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Semi-Supervised Video Object SegmentationonYouTube-VOS 2018
Jaccard (Unseen)· 2020-10-13
77.1
best: 82.2 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Semi-Supervised Video Object SegmentationonYouTube-VOS 2018
Overall· 2020-10-13
82.8
best: 87.5 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonYouTube-VOS 2019
F-Measure (Seen)· 2020-03-18
86.2
best: 90.6 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Foreground-Background Integration arXiv:2003.08333
VideoonYouTube-VOS 2019
F-Measure (Unseen)· 2020-03-18
85.2
best: 90.5 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Foreground-Background Integration arXiv:2003.08333
VideoonYouTube-VOS 2019
Jaccard (Seen)· 2020-03-18
81.7
best: 86.3 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Foreground-Background Integration arXiv:2003.08333
VideoonYouTube-VOS 2019
Mean Jaccard & F-Measure· 2020-03-18
82.6
best: 86.8 (XMem (BL30K,MS))
SOTA
Collaborative Video Object Segmentation by Foreground-Background Integration arXiv:2003.08333
Video Object SegmentationonYouTube-VOS 2019
F-Measure (Seen)· 2020-03-18
86.2
best: 90.6 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Foreground-Background Integration arXiv:2003.08333
Video Object SegmentationonYouTube-VOS 2019
F-Measure (Unseen)· 2020-03-18
85.2
best: 90.5 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Foreground-Background Integration arXiv:2003.08333
Video Object SegmentationonYouTube-VOS 2019
Jaccard (Seen)· 2020-03-18
81.7
best: 86.3 (Cutie+ (base, MEGA))
SOTA
Collaborative Video Object Segmentation by Foreground-Background Integration arXiv:2003.08333
Video Object SegmentationonYouTube-VOS 2019
Mean Jaccard & F-Measure· 2020-03-18
82.6
best: 86.8 (XMem (BL30K,MS))
SOTA
Collaborative Video Object Segmentation by Foreground-Background Integration arXiv:2003.08333
VideoonDAVIS 2017 (test-dev)
Jaccard· 2022-08-01
71.6
best: 78.4 (BATMAN)
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
VideoonDAVIS 2017 (test-dev)
Mean Jaccard & F-Measure· 2022-08-01
75.6
best: 82.2 (BATMAN)
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
Video Object SegmentationonDAVIS 2017 (test-dev)
Jaccard· 2022-08-01
71.6
best: 78.4 (BATMAN)
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
Video Object SegmentationonDAVIS 2017 (test-dev)
Mean Jaccard & F-Measure· 2022-08-01
75.6
best: 82.2 (BATMAN)
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
VideoonDAVIS 2016
F-measure (Mean)· 2020-10-13
91.1
best: 94.7 (SwinB-DeAOT-L)
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonDAVIS 2016
J&F· 2020-10-13
89.9
best: 93.4 (ISVOS (BL30K, MS))
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonDAVIS 2016
Jaccard (Mean)· 2020-10-13
88.7
best: 92.5 (ISVOS (BL30K, MS))
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonYouTube-VOS 2018
F-Measure (Seen)· 2020-10-13
86.6
best: 91 (Cutie+ (base, MEGA))
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonYouTube-VOS 2018
F-Measure (Unseen)· 2020-10-13
85.6
best: 90.2 (XMem (BL30K, MS))
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonYouTube-VOS 2018
Jaccard (Seen)· 2020-10-13
81.8
best: 86.6 (Cutie+ (base, MEGA))
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonYouTube-VOS 2018
Jaccard (Unseen)· 2020-10-13
77.1
best: 82.2 (Cutie+ (base, MEGA))
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
VideoonYouTube-VOS 2018
Speed (FPS)· 2020-10-13
4
best: 65.9 (FRTM)
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonDAVIS 2016
F-measure (Mean)· 2020-10-13
91.1
best: 94.7 (SwinB-DeAOT-L)
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonDAVIS 2016
J&F· 2020-10-13
89.9
best: 93.4 (ISVOS (BL30K, MS))
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonDAVIS 2016
Jaccard (Mean)· 2020-10-13
88.7
best: 92.5 (ISVOS (BL30K, MS))
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonYouTube-VOS 2018
F-Measure (Seen)· 2020-10-13
86.6
best: 91 (Cutie+ (base, MEGA))
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonYouTube-VOS 2018
F-Measure (Unseen)· 2020-10-13
85.6
best: 90.2 (XMem (BL30K, MS))
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonYouTube-VOS 2018
Jaccard (Seen)· 2020-10-13
81.8
best: 86.6 (Cutie+ (base, MEGA))
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonYouTube-VOS 2018
Jaccard (Unseen)· 2020-10-13
77.1
best: 82.2 (Cutie+ (base, MEGA))
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Video Object SegmentationonYouTube-VOS 2018
Speed (FPS)· 2020-10-13
4
best: 65.9 (FRTM)
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Semi-Supervised Video Object SegmentationonDAVIS 2016
F-measure (Mean)· 2020-10-13
91.1
best: 94.7 (SwinB-DeAOT-L)
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Semi-Supervised Video Object SegmentationonDAVIS 2016
J&F· 2020-10-13
89.9
best: 93.4 (ISVOS (BL30K, MS))
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Semi-Supervised Video Object SegmentationonDAVIS 2016
Jaccard (Mean)· 2020-10-13
88.7
best: 92.5 (ISVOS (BL30K, MS))
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349
Semi-Supervised Video Object SegmentationonYouTube-VOS 2018
Speed (FPS)· 2020-10-13
4
best: 65.9 (FRTM)
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration arXiv:2010.06349