paper-with-me

Semantic Segmentation 벤치마크

Semantic Segmentation on COCO (Common Objects in Context)

18개 결과 · ⬇ CSV · JSON

mIoU

26.5 39.17 51.85 64.53 77.2 2021-12 2026-11 Mask2Former (Swin-L, single-scale) — 67.4 (2021-12-02) MaskFormer (Swin-L, single-scale) — 64.8 (2021-12-02) Mask2Former (Swin-L, single-scale) — 67.4 (2021-12-02) MaskFormer (Swin-L, single-scale) — 64.8 (2021-12-02) OneFormer (InternImage-H, emb_dim=1024, single-scale) — 68.8 (2022-11-10) OneFormer (DiNAT-L, single-scale) — 68.1 (2022-11-10) OneFormer (Swin-L, single-scale) — 67.4 (2022-11-10) OneFormer (InternImage-H, emb_dim=1024, single-scale) — 68.8 (2022-11-10) OneFormer (DiNAT-L, single-scale) — 68.1 (2022-11-10) OneFormer (Swin-L, single-scale) — 67.4 (2022-11-10) SegCLIP — 26.5 (2022-11-27) SegCLIP — 26.5 (2022-11-27) HyperSeg — 77.2 (2024-11-26) HyperSeg — 77.2 (2024-11-26) ViT-P (OneFormer, InternImage-H) — 69.1 (2025-05-26) ViT-P (OneFormer, DiNAT-L) — 68.8 (2025-05-26) ViT-P (OneFormer, InternImage-H) — 69.1 (2025-05-26) ViT-P (OneFormer, DiNAT-L) — 68.8 (2025-05-26) Mask2Former (Swin-L, single-scale) — 67.4 (2021-12-02) OneFormer (InternImage-H, emb_dim=1024, single-scale) — 68.8 (2022-11-10) HyperSeg — 77.2 (2024-11-26)
RankModel mIoU Extra Training Data PaperCodeYear
1 HyperSeg 77.2 ✓ HyperSeg: Towards Universal Visual Segmentation with Large Language Model congvvc/HyperSeg 2024
2 ViT-P (OneFormer, InternImage-H) 69.1 The Missing Point in Vision Transformers for Universal Image Segmentation sajjad-sh33/vit-p 2025
3 OneFormer (InternImage-H, emb_dim=1024, single-scale) 68.8 OneFormer: One Transformer to Rule Universal Image Segmentation huggingface/transformers · SHI-Labs/OneFormer · yangyucheng000/University · +1 2022
3 ViT-P (OneFormer, DiNAT-L) 68.8 The Missing Point in Vision Transformers for Universal Image Segmentation sajjad-sh33/vit-p 2025
5 OneFormer (DiNAT-L, single-scale) 68.1 OneFormer: One Transformer to Rule Universal Image Segmentation huggingface/transformers · SHI-Labs/OneFormer · yangyucheng000/University · +1 2022
6 OneFormer (Swin-L, single-scale) 67.4 OneFormer: One Transformer to Rule Universal Image Segmentation huggingface/transformers · SHI-Labs/OneFormer · yangyucheng000/University · +1 2022
6 Mask2Former (Swin-L, single-scale) 67.4 Masked-attention Mask Transformer for Universal Image Segmentation huggingface/transformers · open-mmlab/mmdetection · facebookresearch/Mask2Former · +4 2021
8 MaskFormer (Swin-L, single-scale) 64.8 Masked-attention Mask Transformer for Universal Image Segmentation huggingface/transformers · open-mmlab/mmdetection · facebookresearch/Mask2Former · +4 2021
9 SegCLIP 26.5 SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation arrowluo/segclip 2022
10 HyperSeg 77.2 ✓ HyperSeg: Towards Universal Visual Segmentation with Large Language Model congvvc/HyperSeg 2024
11 ViT-P (OneFormer, InternImage-H) 69.1 The Missing Point in Vision Transformers for Universal Image Segmentation sajjad-sh33/vit-p 2025
12 OneFormer (InternImage-H, emb_dim=1024, single-scale) 68.8 OneFormer: One Transformer to Rule Universal Image Segmentation huggingface/transformers · SHI-Labs/OneFormer · yangyucheng000/University · +1 2022
12 ViT-P (OneFormer, DiNAT-L) 68.8 The Missing Point in Vision Transformers for Universal Image Segmentation sajjad-sh33/vit-p 2025
14 OneFormer (DiNAT-L, single-scale) 68.1 OneFormer: One Transformer to Rule Universal Image Segmentation huggingface/transformers · SHI-Labs/OneFormer · yangyucheng000/University · +1 2022
15 OneFormer (Swin-L, single-scale) 67.4 OneFormer: One Transformer to Rule Universal Image Segmentation huggingface/transformers · SHI-Labs/OneFormer · yangyucheng000/University · +1 2022
15 Mask2Former (Swin-L, single-scale) 67.4 Masked-attention Mask Transformer for Universal Image Segmentation huggingface/transformers · open-mmlab/mmdetection · facebookresearch/Mask2Former · +4 2021
17 MaskFormer (Swin-L, single-scale) 64.8 Masked-attention Mask Transformer for Universal Image Segmentation huggingface/transformers · open-mmlab/mmdetection · facebookresearch/Mask2Former · +4 2021
18 SegCLIP 26.5 SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation arrowluo/segclip 2022
1–18 / 18 페이지당 10 20 50 100