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/HyperSeg

HyperSeg

Reported on 24 benchmarks across 7 tasks · 1 paper · 11 SOTA

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

Computer Vision22 results

Instance SegmentationonRefCOCO testA
Overall IoU· uses extra data· 2024-11-26
85.7
best: 86.49 (DeRIS-L)
SOTA
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606
Instance SegmentationonRefCoCo val
Overall IoU· uses extra data· 2024-11-26
84.8
best: 85.41 (DeRIS-L)
SOTA
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606
Instance SegmentationonRefCOCO testB
Overall IoU· uses extra data· 2024-11-26
83.4
SOTA
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606
Instance SegmentationonRefCOCO+ testA
Overall IoU· uses extra data· 2024-11-26
83.5
SOTA
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606
Referring Expression SegmentationonRefCOCO testA
Overall IoU· uses extra data· 2024-11-26
85.7
best: 86.49 (DeRIS-L)
SOTA
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606
Referring Expression SegmentationonRefCoCo val
Overall IoU· uses extra data· 2024-11-26
84.8
best: 85.41 (DeRIS-L)
SOTA
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606
Referring Expression SegmentationonRefCOCO testB
Overall IoU· uses extra data· 2024-11-26
83.4
SOTA
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606
Referring Expression SegmentationonRefCOCO+ testA
Overall IoU· uses extra data· 2024-11-26
83.5
SOTA
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606
Open Vocabulary Semantic SegmentationonPASCAL Context-59
mIoU· uses extra data· 2024-11-26
64.6
SOTA
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606
VideoonRefer-YouTube-VOS
J&F· uses extra data· 2024-11-26
68.5
best: 73.7 (FindTrack)
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606
Instance SegmentationonRefCOCOg-test
Overall IoU· uses extra data· 2024-11-26
78.9
best: 80.54 (UniLSeg-100)
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606
Instance SegmentationonRefCOCO+ val
Overall IoU· uses extra data· 2024-11-26
79
best: 79.4 (MLCD-Seg-7B)
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606
Instance SegmentationonRefCOCO+ test B
Overall IoU· uses extra data· 2024-11-26
75.2
best: 75.6 (MLCD-Seg-7B)
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606
Instance SegmentationonDAVIS 2017 (val)
J&F 1st frame· uses extra data· 2024-11-26
71.2
best: 72.5 (UNINEXT-H)
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606
Instance SegmentationonRefCOCOg-val
Overall IoU· uses extra data· 2024-11-26
79.4
best: 79.9 (MLCD-Seg-7B)
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606
Video Object SegmentationonRefer-YouTube-VOS
J&F· uses extra data· 2024-11-26
68.5
best: 73.7 (FindTrack)
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606
Referring Expression SegmentationonRefCOCOg-test
Overall IoU· uses extra data· 2024-11-26
78.9
best: 80.54 (UniLSeg-100)
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606
Referring Expression SegmentationonRefCOCO+ val
Overall IoU· uses extra data· 2024-11-26
79
best: 79.4 (MLCD-Seg-7B)
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606
Referring Expression SegmentationonRefCOCO+ test B
Overall IoU· uses extra data· 2024-11-26
75.2
best: 75.6 (MLCD-Seg-7B)
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606
Referring Expression SegmentationonDAVIS 2017 (val)
J&F 1st frame· uses extra data· 2024-11-26
71.2
best: 72.5 (UNINEXT-H)
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606
Referring Expression SegmentationonRefCOCOg-val
Overall IoU· uses extra data· 2024-11-26
79.4
best: 79.9 (MLCD-Seg-7B)
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606
Open Vocabulary Semantic SegmentationonPascalVOC-20
mIoU· uses extra data· 2024-11-26
92.1
best: 97.9 (UMG-CLIP-L/14)
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606

Medical1 result

Semantic SegmentationonCOCO (Common Objects in Context)
mIoU· uses extra data· 2024-11-26
77.2
SOTA
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606

Audio1 result

10-shot image generationonCOCO (Common Objects in Context)
mIoU· uses extra data· 2024-11-26
77.2
SOTA
HyperSeg: Towards Universal Visual Segmentation with Large Language Model arXiv:2411.17606