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/DeVIS (ResNet-50)

DeVIS (ResNet-50)

Reported on 15 benchmarks across 1 task · 1 paper

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

Computer Vision15 results

Video Instance SegmentationonYouTube-VIS 2021
AP50· 2022-07-22
66.8
best: 87.3 (CAVIS(VIT-L, Offline))
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation arXiv:2207.11103
Video Instance SegmentationonYouTube-VIS 2021
AP75· 2022-07-22
46.6
best: 73.2 (CAVIS(VIT-L, Offline))
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation arXiv:2207.11103
Video Instance SegmentationonYouTube-VIS 2021
AR1· 2022-07-22
38
best: 49.7 (CAVIS(VIT-L, Offline))
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation arXiv:2207.11103
Video Instance SegmentationonYouTube-VIS 2021
AR10· 2022-07-22
50.1
best: 70.7 (DVIS-DAQ(VIT-L, Offline))
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation arXiv:2207.11103
Video Instance SegmentationonYouTube-VIS 2021
mask AP· 2022-07-22
43.1
best: 65.3 (CAVIS(VIT-L, Offline))
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation arXiv:2207.11103
Video Instance SegmentationonYouTube-VIS validation
AP50· 2022-07-22
66.7
best: 89.3 (CAVIS(ViT-L, Online))
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation arXiv:2207.11103
Video Instance SegmentationonYouTube-VIS validation
AP75· 2022-07-22
48.6
best: 76.2 (CAVIS(ViT-L, Online))
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation arXiv:2207.11103
Video Instance SegmentationonYouTube-VIS validation
AR1· 2022-07-22
42.4
best: 58.3 (CAVIS(ViT-L, Online))
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation arXiv:2207.11103
Video Instance SegmentationonYouTube-VIS validation
AR10· 2022-07-22
51.6
best: 73.7 (DVIS++(ViT-L, Online))
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation arXiv:2207.11103
Video Instance SegmentationonYouTube-VIS validation
mask AP· 2022-07-22
44.4
best: 68.9 (CAVIS(ViT-L, Online))
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation arXiv:2207.11103
Video Instance SegmentationonOVIS validation
AP50· 2022-07-22
47.6
best: 83.8 (DVIS-DAQ(VIT-L, Offline))
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation arXiv:2207.11103
Video Instance SegmentationonOVIS validation
AP75· 2022-07-22
20.8
best: 63.5 (CAVIS(VIT-L, Offline))
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation arXiv:2207.11103
Video Instance SegmentationonOVIS validation
AR1· 2022-07-22
12
best: 21.2 (CAVIS(VIT-L, Offline))
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation arXiv:2207.11103
Video Instance SegmentationonOVIS validation
AR10· 2022-07-22
28.9
best: 61.8 (CAVIS(VIT-L, Offline))
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation arXiv:2207.11103
Video Instance SegmentationonOVIS validation
mask AP· 2022-07-22
23.7
best: 57.1 (DVIS-DAQ(VIT-L, Offline))
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation arXiv:2207.11103