paper-with-me

Weakly-Supervised Semantic Segmentation 벤치마크

Weakly-Supervised Semantic Segmentation on PASCAL VOC 2012 train

8개 결과 · ⬇ CSV · JSON

Mean IoU

71.4 73.65 75.9 78.15 80.4 2022-10 2026-09 ViT-PCM — 71.4 (2022-10-31) ViT-PCM — 71.4 (2022-10-31) WeakTr (DeiT-S, single-stage) — 76.5 (2023-04-03) WeakTr (DeiT-S, single-stage) — 76.5 (2023-04-03) FMA-WSSS — 80.4 (2023-12-06) FMA-WSSS — 80.4 (2023-12-06) FBR — 75.9 (2024-06-22) FBR — 75.9 (2024-06-22) ViT-PCM — 71.4 (2022-10-31) WeakTr (DeiT-S, single-stage) — 76.5 (2023-04-03) FMA-WSSS — 80.4 (2023-12-06)
RankModel Mean IoU Extra Training Data PaperCodeYear
1 FMA-WSSS 80.4 Foundation Model Assisted Weakly Supervised Semantic Segmentation HAL-42/FMA-WSSS 2023
2 WeakTr (DeiT-S, single-stage) 76.5 WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation hustvl/weaktr 2023
3 FBR 75.9 Fine-grained Background Representation for Weakly Supervised Semantic Segmentation YininKorea/FBR 2024
4 ViT-PCM 71.4 Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation deepplants/vit-pcm 2022
5 FMA-WSSS 80.4 Foundation Model Assisted Weakly Supervised Semantic Segmentation HAL-42/FMA-WSSS 2023
6 WeakTr (DeiT-S, single-stage) 76.5 WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation hustvl/weaktr 2023
7 FBR 75.9 Fine-grained Background Representation for Weakly Supervised Semantic Segmentation YininKorea/FBR 2024
8 ViT-PCM 71.4 Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation deepplants/vit-pcm 2022
1–8 / 8 페이지당 10 20 50 100