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(Swin-L)

DVIS(Swin-L)

Reported on 16 benchmarks across 4 tasks · 1 paper · 14 SOTA

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

Computer Vision12 results

Video Instance SegmentationonYouTube-VIS 2021
AP50· uses extra data· 2023-06-06
83
best: 87.3 (CAVIS(VIT-L, Offline))
SOTA
DVIS: Decoupled Video Instance Segmentation Framework arXiv:2306.03413
Video Instance SegmentationonYouTube-VIS 2021
AP75· uses extra data· 2023-06-06
68.4
best: 73.2 (CAVIS(VIT-L, Offline))
SOTA
DVIS: Decoupled Video Instance Segmentation Framework arXiv:2306.03413
Video Instance SegmentationonYouTube-VIS 2021
AR10· uses extra data· 2023-06-06
65.7
best: 70.7 (DVIS-DAQ(VIT-L, Offline))
SOTA
DVIS: Decoupled Video Instance Segmentation Framework arXiv:2306.03413
Video Instance SegmentationonYoutube-VIS 2022 Validation
AP50_L· uses extra data· 2023-06-06
69
best: 75.7 (DVIS++(VIT-L))
SOTA
DVIS: Decoupled Video Instance Segmentation Framework arXiv:2306.03413
Video Instance SegmentationonYoutube-VIS 2022 Validation
AP75_L· uses extra data· 2023-06-06
48.8
best: 52.8 (DVIS++(VIT-L))
SOTA
DVIS: Decoupled Video Instance Segmentation Framework arXiv:2306.03413
Video Instance SegmentationonYoutube-VIS 2022 Validation
AR10_L· uses extra data· 2023-06-06
51.8
best: 55.8 (DVIS++(VIT-L))
SOTA
DVIS: Decoupled Video Instance Segmentation Framework arXiv:2306.03413
Video Instance SegmentationonYoutube-VIS 2022 Validation
AR1_L· uses extra data· 2023-06-06
37.2
best: 40.6 (DVIS++(VIT-L))
SOTA
DVIS: Decoupled Video Instance Segmentation Framework arXiv:2306.03413
Video Instance SegmentationonYoutube-VIS 2022 Validation
mAP_L· uses extra data· 2023-06-06
45.9
best: 50.9 (DVIS++(VIT-L))
SOTA
DVIS: Decoupled Video Instance Segmentation Framework arXiv:2306.03413
Panoptic SegmentationonVIPSeg
STQ· 2023-06-06
55.3
best: 58.2 (UniVS(Swin-L))
SOTA
DVIS: Decoupled Video Instance Segmentation Framework arXiv:2306.03413
Panoptic SegmentationonVIPSeg
VPQ· 2023-06-06
57.6
best: 58.5 (CAVIS(VIT-L))
SOTA
DVIS: Decoupled Video Instance Segmentation Framework arXiv:2306.03413
Video Instance SegmentationonYouTube-VIS 2021
AR1· uses extra data· 2023-06-06
47.7
best: 49.7 (CAVIS(VIT-L, Offline))
DVIS: Decoupled Video Instance Segmentation Framework arXiv:2306.03413
Video Instance SegmentationonYouTube-VIS 2021
mask AP· uses extra data· 2023-06-06
60.1
best: 65.3 (CAVIS(VIT-L, Offline))
DVIS: Decoupled Video Instance Segmentation Framework arXiv:2306.03413

Medical2 results

Semantic SegmentationonVIPSeg
STQ· 2023-06-06
55.3
best: 58.2 (UniVS(Swin-L))
SOTA
DVIS: Decoupled Video Instance Segmentation Framework arXiv:2306.03413
Semantic SegmentationonVIPSeg
VPQ· 2023-06-06
57.6
best: 58.5 (CAVIS(VIT-L))
SOTA
DVIS: Decoupled Video Instance Segmentation Framework arXiv:2306.03413

Audio2 results

10-shot image generationonVIPSeg
STQ· 2023-06-06
55.3
best: 58.2 (UniVS(Swin-L))
SOTA
DVIS: Decoupled Video Instance Segmentation Framework arXiv:2306.03413
10-shot image generationonVIPSeg
VPQ· 2023-06-06
57.6
best: 58.5 (CAVIS(VIT-L))
SOTA
DVIS: Decoupled Video Instance Segmentation Framework arXiv:2306.03413