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/KMN

KMN

Reported on 79 benchmarks across 5 tasks · 2 papers · 59 SOTA

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

Computer Vision87 results

VideoonDAVIS 2017 (test-dev)
F-measure· 2020-07-16
80.3
best: 86.1 (BATMAN)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonDAVIS 2017 (test-dev)
Jaccard· 2020-07-16
74.1
best: 78.4 (BATMAN)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonDAVIS 2017 (test-dev)
Mean Jaccard & F-Measure· 2020-07-16
77.2
best: 82.2 (BATMAN)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonYouTube-VOS 2018
F-Measure (Unseen)· 2020-07-16
83.3
best: 90.2 (XMem (BL30K, MS))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonYouTube-VOS 2018
Jaccard (Seen)· 2020-07-16
81.4
best: 86.6 (Cutie+ (base, MEGA))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonYouTube-VOS 2018
Mean Jaccard & F-Measure· 2020-07-16
81.4
best: 86.9 (XMem (BL30K, MS))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonDAVIS 2017 (val)
F-measure· 2020-07-16
85.6
best: 92.6 (XMem (BLK30K, MS))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonDAVIS 2017 (val)
Jaccard· 2020-07-16
80
best: 86.3 (XMem (BLK30K, MS))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonDAVIS 2017 (val)
Mean Jaccard & F-Measure· 2020-07-16
82.8
best: 89.5 (XMem (BLK30K, MS))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonDAVIS 2017 (val)
F-measure (Mean)· 2020-07-16
85.6
best: 93.4 (Cutie+ (base))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonDAVIS 2017 (val)
J&F· 2020-07-16
82.8
best: 90.7 (SAM2)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonDAVIS 2017 (val)
Jaccard (Mean)· 2020-07-16
80
best: 87.5 (Cutie+ (base))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonDAVIS 2016
F-measure (Mean)· 2020-07-16
91.5
best: 94.7 (SwinB-DeAOT-L)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonDAVIS 2016
J&F· 2020-07-16
90.5
best: 93.4 (ISVOS (BL30K, MS))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonDAVIS 2016
Jaccard (Mean)· 2020-07-16
89.5
best: 92.5 (ISVOS (BL30K, MS))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonDAVIS 2017 (test-dev)
F-measure (Mean)· 2020-07-16
80.3
best: 91.4 (Cutie+ (base, MEGA))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonDAVIS 2017 (test-dev)
J&F· 2020-07-16
77.2
best: 88.1 (Cutie+ (base, MEGA))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonDAVIS 2017 (test-dev)
Jaccard (Mean)· 2020-07-16
74.1
best: 84.7 (Cutie+ (base, MEGA))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonDAVIS (no YouTube-VOS training)
D16 val (G)· 2020-07-16
87.6
best: 89.4 (HMMN)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonDAVIS (no YouTube-VOS training)
D17 val (F)· 2020-07-16
77.8
best: 83.1 (HMMN)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonDAVIS (no YouTube-VOS training)
D17 val (G)· 2020-07-16
76
best: 80.4 (HMMN)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonDAVIS (no YouTube-VOS training)
D17 val (J)· 2020-07-16
74.2
best: 77.7 (HMMN)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonDAVIS 2017 (test-dev)
F-measure· 2020-07-16
80.3
best: 86.1 (BATMAN)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonDAVIS 2017 (test-dev)
Jaccard· 2020-07-16
74.1
best: 78.4 (BATMAN)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonDAVIS 2017 (test-dev)
Mean Jaccard & F-Measure· 2020-07-16
77.2
best: 82.2 (BATMAN)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonYouTube-VOS 2018
F-Measure (Unseen)· 2020-07-16
83.3
best: 90.2 (XMem (BL30K, MS))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonYouTube-VOS 2018
Jaccard (Seen)· 2020-07-16
81.4
best: 86.6 (Cutie+ (base, MEGA))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonYouTube-VOS 2018
Mean Jaccard & F-Measure· 2020-07-16
81.4
best: 86.9 (XMem (BL30K, MS))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonDAVIS 2017 (val)
F-measure· 2020-07-16
85.6
best: 92.6 (XMem (BLK30K, MS))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonDAVIS 2017 (val)
Jaccard· 2020-07-16
80
best: 86.3 (XMem (BLK30K, MS))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonDAVIS 2017 (val)
Mean Jaccard & F-Measure· 2020-07-16
82.8
best: 89.5 (XMem (BLK30K, MS))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonDAVIS 2017 (val)
F-measure (Mean)· 2020-07-16
85.6
best: 93.4 (Cutie+ (base))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonDAVIS 2017 (val)
J&F· 2020-07-16
82.8
best: 90.7 (SAM2)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonDAVIS 2017 (val)
Jaccard (Mean)· 2020-07-16
80
best: 87.5 (Cutie+ (base))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonDAVIS 2016
F-measure (Mean)· 2020-07-16
91.5
best: 94.7 (SwinB-DeAOT-L)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonDAVIS 2016
J&F· 2020-07-16
90.5
best: 93.4 (ISVOS (BL30K, MS))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonDAVIS 2016
Jaccard (Mean)· 2020-07-16
89.5
best: 92.5 (ISVOS (BL30K, MS))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonDAVIS 2017 (test-dev)
F-measure (Mean)· 2020-07-16
80.3
best: 91.4 (Cutie+ (base, MEGA))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonDAVIS 2017 (test-dev)
J&F· 2020-07-16
77.2
best: 88.1 (Cutie+ (base, MEGA))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonDAVIS 2017 (test-dev)
Jaccard (Mean)· 2020-07-16
74.1
best: 84.7 (Cutie+ (base, MEGA))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonDAVIS (no YouTube-VOS training)
D16 val (G)· 2020-07-16
87.6
best: 89.4 (HMMN)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 val (F)· 2020-07-16
77.8
best: 83.1 (HMMN)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 val (G)· 2020-07-16
76
best: 80.4 (HMMN)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 val (J)· 2020-07-16
74.2
best: 77.7 (HMMN)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
F-measure (Mean)· 2020-07-16
85.6
best: 93.4 (Cutie+ (base))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
J&F· 2020-07-16
82.8
best: 90.7 (SAM2)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
Jaccard (Mean)· 2020-07-16
80
best: 87.5 (Cutie+ (base))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Semi-Supervised Video Object SegmentationonDAVIS 2016
F-measure (Mean)· 2020-07-16
91.5
best: 94.7 (SwinB-DeAOT-L)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Semi-Supervised Video Object SegmentationonDAVIS 2016
J&F· 2020-07-16
90.5
best: 93.4 (ISVOS (BL30K, MS))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Semi-Supervised Video Object SegmentationonDAVIS 2016
Jaccard (Mean)· 2020-07-16
89.5
best: 92.5 (ISVOS (BL30K, MS))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
F-measure (Mean)· 2020-07-16
80.3
best: 91.4 (Cutie+ (base, MEGA))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
J&F· 2020-07-16
77.2
best: 88.1 (Cutie+ (base, MEGA))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
Jaccard (Mean)· 2020-07-16
74.1
best: 84.7 (Cutie+ (base, MEGA))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
D16 val (G)· 2020-07-16
87.6
best: 89.4 (HMMN)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 val (F)· 2020-07-16
77.8
best: 83.1 (HMMN)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 val (G)· 2020-07-16
76
best: 80.4 (HMMN)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 val (J)· 2020-07-16
74.2
best: 77.7 (HMMN)
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Semi-Supervised Video Object SegmentationonYouTube-VOS 2018
F-Measure (Unseen)· uses extra data· 2020-07-16
83.3
best: 90.2 (XMem (BL30K, MS))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Semi-Supervised Video Object SegmentationonYouTube-VOS 2018
Jaccard (Seen)· uses extra data· 2020-07-16
81.4
best: 86.6 (Cutie+ (base, MEGA))
SOTA
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonYouTube-VOS 2018
Jaccard (Unseen)· 2022-08-01
75.3
best: 82.2 (Cutie+ (base, MEGA))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
VideoonYouTube-VOS 2018
Jaccard (Unseen)· uses extra data· 2022-08-01
75.3
best: 82.2 (Cutie+ (base, MEGA))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
Object TrackingonYouTube-VOS 2018
Jaccard (Unseen)· 2022-08-01
75.3
best: 75.7 (RMN)
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
Video Object SegmentationonYouTube-VOS 2018
Jaccard (Unseen)· 2022-08-01
75.3
best: 82.2 (Cutie+ (base, MEGA))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
Video Object SegmentationonYouTube-VOS 2018
Jaccard (Unseen)· uses extra data· 2022-08-01
75.3
best: 82.2 (Cutie+ (base, MEGA))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
Semi-Supervised Video Object SegmentationonYouTube-VOS 2018
Jaccard (Unseen)· uses extra data· 2022-08-01
75.3
best: 82.2 (Cutie+ (base, MEGA))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
Visual Object TrackingonYouTube-VOS 2018
Jaccard (Unseen)· 2022-08-01
75.3
best: 75.7 (RMN)
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
VideoonYouTube-VOS 2018
F-Measure (Seen)· 2020-07-16
85.6
best: 91 (Cutie+ (base, MEGA))
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonDAVIS (no YouTube-VOS training)
D16 val (F)· 2020-07-16
88.1
best: 90.6 (HMMN)
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonDAVIS (no YouTube-VOS training)
D16 val (J)· 2020-07-16
87.1
best: 88.2 (HMMN)
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonDAVIS (no YouTube-VOS training)
FPS· 2020-07-16
8.33
best: 50.1 (TBD)
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonYouTube-VOS 2018
F-Measure (Seen)· uses extra data· 2020-07-16
85.6
best: 91 (Cutie+ (base, MEGA))
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonYouTube-VOS 2018
F-Measure (Unseen)· uses extra data· 2020-07-16
83.3
best: 90.2 (XMem (BL30K, MS))
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonYouTube-VOS 2018
Jaccard (Seen)· uses extra data· 2020-07-16
81.4
best: 86.6 (Cutie+ (base, MEGA))
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
VideoonYouTube-VOS 2018
Overall· uses extra data· 2020-07-16
81.4
best: 87.5 (Cutie+ (base, MEGA))
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonYouTube-VOS 2018
F-Measure (Seen)· 2020-07-16
85.6
best: 91 (Cutie+ (base, MEGA))
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonDAVIS (no YouTube-VOS training)
D16 val (F)· 2020-07-16
88.1
best: 90.6 (HMMN)
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonDAVIS (no YouTube-VOS training)
D16 val (J)· 2020-07-16
87.1
best: 88.2 (HMMN)
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonDAVIS (no YouTube-VOS training)
FPS· 2020-07-16
8.33
best: 50.1 (TBD)
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonYouTube-VOS 2018
F-Measure (Seen)· uses extra data· 2020-07-16
85.6
best: 91 (Cutie+ (base, MEGA))
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonYouTube-VOS 2018
F-Measure (Unseen)· uses extra data· 2020-07-16
83.3
best: 90.2 (XMem (BL30K, MS))
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonYouTube-VOS 2018
Jaccard (Seen)· uses extra data· 2020-07-16
81.4
best: 86.6 (Cutie+ (base, MEGA))
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Video Object SegmentationonYouTube-VOS 2018
Overall· uses extra data· 2020-07-16
81.4
best: 87.5 (Cutie+ (base, MEGA))
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
D16 val (F)· 2020-07-16
88.1
best: 90.6 (HMMN)
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
D16 val (J)· 2020-07-16
87.1
best: 88.2 (HMMN)
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
FPS· 2020-07-16
8.33
best: 50.1 (TBD)
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Semi-Supervised Video Object SegmentationonYouTube-VOS 2018
F-Measure (Seen)· uses extra data· 2020-07-16
85.6
best: 91 (Cutie+ (base, MEGA))
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270
Semi-Supervised Video Object SegmentationonYouTube-VOS 2018
Overall· uses extra data· 2020-07-16
81.4
best: 87.5 (Cutie+ (base, MEGA))
Kernelized Memory Network for Video Object Segmentation arXiv:2007.08270