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/ViT-P (InternImage-H)

ViT-P (InternImage-H)

Reported on 8 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Medical4 results

Semantic SegmentationonADE20K
Validation mIoU· uses extra data· 2025-05-26
63.6
SOTA
The Missing Point in Vision Transformers for Universal Image Segmentation arXiv:2505.19795
Semantic SegmentationonCityscapes val
mIoU· uses extra data· 2025-05-26
87.4
best: 90.3 (EfficientPS (Cityscapes-fine))
The Missing Point in Vision Transformers for Universal Image Segmentation arXiv:2505.19795
Semantic SegmentationonCOCO-Stuff test
mIoU· 2025-05-26
53.5
best: 53.7 (VPNeXt)
The Missing Point in Vision Transformers for Universal Image Segmentation arXiv:2505.19795
Semantic SegmentationonADE20K
Params (M)· uses extra data· 2025-05-26
1610
best: 3000 (FD-SwinV2-G)
The Missing Point in Vision Transformers for Universal Image Segmentation arXiv:2505.19795

Audio4 results

10-shot image generationonADE20K
Validation mIoU· uses extra data· 2025-05-26
63.6
SOTA
The Missing Point in Vision Transformers for Universal Image Segmentation arXiv:2505.19795
10-shot image generationonCityscapes val
mIoU· uses extra data· 2025-05-26
87.4
best: 90.3 (EfficientPS (Cityscapes-fine))
The Missing Point in Vision Transformers for Universal Image Segmentation arXiv:2505.19795
10-shot image generationonCOCO-Stuff test
mIoU· 2025-05-26
53.5
best: 53.7 (VPNeXt)
The Missing Point in Vision Transformers for Universal Image Segmentation arXiv:2505.19795
10-shot image generationonADE20K
Params (M)· uses extra data· 2025-05-26
1610
best: 3000 (FD-SwinV2-G)
The Missing Point in Vision Transformers for Universal Image Segmentation arXiv:2505.19795