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/DVIS++(VIT-L)

DVIS++(VIT-L)

Reported on 15 benchmarks across 8 tasks · 1 paper · 12 SOTA

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

Computer Vision10 results

Scene ParsingonVSPW
mIoU· 2023-12-20
63.8
SOTA
DVIS++: Improved Decoupled Framework for Universal Video Segmentation arXiv:2312.13305
Video Semantic SegmentationonVSPW
mIoU· 2023-12-20
63.8
SOTA
DVIS++: Improved Decoupled Framework for Universal Video Segmentation arXiv:2312.13305
Scene UnderstandingonVSPW
mIoU· 2023-12-20
63.8
SOTA
DVIS++: Improved Decoupled Framework for Universal Video Segmentation arXiv:2312.13305
Video Instance SegmentationonYoutube-VIS 2022 Validation
AP50_L· uses extra data· 2023-12-20
75.7
SOTA
DVIS++: Improved Decoupled Framework for Universal Video Segmentation arXiv:2312.13305
Video Instance SegmentationonYoutube-VIS 2022 Validation
AP75_L· uses extra data· 2023-12-20
52.8
SOTA
DVIS++: Improved Decoupled Framework for Universal Video Segmentation arXiv:2312.13305
Video Instance SegmentationonYoutube-VIS 2022 Validation
AR10_L· uses extra data· 2023-12-20
55.8
SOTA
DVIS++: Improved Decoupled Framework for Universal Video Segmentation arXiv:2312.13305
Video Instance SegmentationonYoutube-VIS 2022 Validation
AR1_L· uses extra data· 2023-12-20
40.6
SOTA
DVIS++: Improved Decoupled Framework for Universal Video Segmentation arXiv:2312.13305
Video Instance SegmentationonYoutube-VIS 2022 Validation
mAP_L· uses extra data· 2023-12-20
50.9
SOTA
DVIS++: Improved Decoupled Framework for Universal Video Segmentation arXiv:2312.13305
Panoptic SegmentationonVIPSeg
STQ· 2023-12-20
56
best: 58.2 (UniVS(Swin-L))
SOTA
DVIS++: Improved Decoupled Framework for Universal Video Segmentation arXiv:2312.13305
Panoptic SegmentationonVIPSeg
VPQ· 2023-12-20
58
best: 58.5 (CAVIS(VIT-L))
DVIS++: Improved Decoupled Framework for Universal Video Segmentation arXiv:2312.13305

Audio3 results

2D Semantic SegmentationonVSPW
mIoU· 2023-12-20
63.8
SOTA
DVIS++: Improved Decoupled Framework for Universal Video Segmentation arXiv:2312.13305
10-shot image generationonVIPSeg
STQ· 2023-12-20
56
best: 58.2 (UniVS(Swin-L))
SOTA
DVIS++: Improved Decoupled Framework for Universal Video Segmentation arXiv:2312.13305
10-shot image generationonVIPSeg
VPQ· 2023-12-20
58
best: 58.5 (CAVIS(VIT-L))
DVIS++: Improved Decoupled Framework for Universal Video Segmentation arXiv:2312.13305

Medical2 results

Semantic SegmentationonVIPSeg
STQ· 2023-12-20
56
best: 58.2 (UniVS(Swin-L))
SOTA
DVIS++: Improved Decoupled Framework for Universal Video Segmentation arXiv:2312.13305
Semantic SegmentationonVIPSeg
VPQ· 2023-12-20
58
best: 58.5 (CAVIS(VIT-L))
DVIS++: Improved Decoupled Framework for Universal Video Segmentation arXiv:2312.13305