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-PCM

ViT-PCM

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 SegmentationonPASCAL VOC 2012 train
Mean IoU· 2022-10-31
71.4
best: 80.4 (FMA-WSSS)
SOTA
Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation arXiv:2210.17400
Semantic SegmentationonCOCO 2014 val
mIoU· 2022-10-31
45
best: 56.8 (DHR (Swin-L, Mask2Former))
Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation arXiv:2210.17400
Semantic SegmentationonPASCAL VOC 2012 val
Mean IoU· 2022-10-31
70.3
best: 83.4 (SemPLeS (Swin-L))
Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation arXiv:2210.17400
Semantic SegmentationonPASCAL VOC 2012 test
Mean IoU· 2022-10-31
70.9
best: 82.9 (SemPLeS (Swin-L))
Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation arXiv:2210.17400

Audio4 results

10-shot image generationonPASCAL VOC 2012 train
Mean IoU· 2022-10-31
71.4
best: 80.4 (FMA-WSSS)
SOTA
Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation arXiv:2210.17400
10-shot image generationonCOCO 2014 val
mIoU· 2022-10-31
45
best: 56.8 (DHR (Swin-L, Mask2Former))
Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation arXiv:2210.17400
10-shot image generationonPASCAL VOC 2012 val
Mean IoU· 2022-10-31
70.3
best: 83.4 (SemPLeS (Swin-L))
Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation arXiv:2210.17400
10-shot image generationonPASCAL VOC 2012 test
Mean IoU· 2022-10-31
70.9
best: 82.9 (SemPLeS (Swin-L))
Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation arXiv:2210.17400