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/TransFGU (ViT-S/8)

TransFGU (ViT-S/8)

Reported on 12 benchmarks across 3 tasks · 1 paper · 9 SOTA

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

Medical4 results

Semantic SegmentationonCOCO-Stuff-81
Pixel Accuracy· 2021-12-02
64.3
best: 78.8 (CAUSE-MLP (ViT-S/8))
SOTA
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation arXiv:2112.01515
Semantic SegmentationonCOCO-Stuff-81
mIoU· 2021-12-02
12.7
best: 21.2 (CAUSE-TR (ViT-S/8))
SOTA
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation arXiv:2112.01515
Semantic SegmentationonCOCO-Stuff-171
Pixel Accuracy· uses extra data· 2021-12-02
34.32
best: 46.6 (CAUSE-TR (ViT-S/8))
SOTA
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation arXiv:2112.01515
Semantic SegmentationonCOCO-Stuff-171
mIoU· uses extra data· 2021-12-02
11.93
best: 34 (CorrCLIP)
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation arXiv:2112.01515

Computer Vision4 results

Unsupervised Semantic SegmentationonCOCO-Stuff-81
Pixel Accuracy· 2021-12-02
64.3
best: 78.8 (CAUSE-MLP (ViT-S/8))
SOTA
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation arXiv:2112.01515
Unsupervised Semantic SegmentationonCOCO-Stuff-81
mIoU· 2021-12-02
12.7
best: 21.2 (CAUSE-TR (ViT-S/8))
SOTA
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation arXiv:2112.01515
Unsupervised Semantic SegmentationonCOCO-Stuff-171
Pixel Accuracy· uses extra data· 2021-12-02
34.32
best: 46.6 (CAUSE-TR (ViT-S/8))
SOTA
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation arXiv:2112.01515
Unsupervised Semantic SegmentationonCOCO-Stuff-171
mIoU· uses extra data· 2021-12-02
11.93
best: 34 (CorrCLIP)
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation arXiv:2112.01515

Audio4 results

10-shot image generationonCOCO-Stuff-81
Pixel Accuracy· 2021-12-02
64.3
best: 78.8 (CAUSE-MLP (ViT-S/8))
SOTA
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation arXiv:2112.01515
10-shot image generationonCOCO-Stuff-81
mIoU· 2021-12-02
12.7
best: 21.2 (CAUSE-TR (ViT-S/8))
SOTA
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation arXiv:2112.01515
10-shot image generationonCOCO-Stuff-171
Pixel Accuracy· uses extra data· 2021-12-02
34.32
best: 46.6 (CAUSE-TR (ViT-S/8))
SOTA
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation arXiv:2112.01515
10-shot image generationonCOCO-Stuff-171
mIoU· uses extra data· 2021-12-02
11.93
best: 34 (CorrCLIP)
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation arXiv:2112.01515