paper-with-me

Semantic Segmentation 벤치마크

Semantic Segmentation on Mapillary val

16개 결과 · ⬇ CSV · JSON

mIoU

32.93 43.7 54.47 65.23 76 2019-09 2026-11 NiseNet — 48.32 (2019-09-24) NiseNet — 48.32 (2019-09-24) SegBlocks-RN50 (t=0.4) — 39.7 (2020-11-24) SegBlocks-RN50 (t=0.4) — 39.7 (2020-11-24) MaskFormer (ResNet-50) — 55.4 (2021-07-13) MaskFormer (ResNet-50) — 55.4 (2021-07-13) Mask2Former (Swin-L, multiscale) — 64.7 (2021-12-02) Mask2Former (Swin-L, multiscale) — 64.7 (2021-12-02) OneFormer (DiNAT-L, multi-scale) — 64.9 (2022-11-10) OneFormer (DiNAT-L, multi-scale) — 64.9 (2022-11-10) AO-SegNet — 76.0 (2023-07-07) AO-SegNet — 76.0 (2023-07-07) MRFP+(Ours) Resnet50 — 44.93 (2023-11-30) Resnet50 — 32.93 (2023-11-30) MRFP+(Ours) Resnet50 — 44.93 (2023-11-30) Resnet50 — 32.93 (2023-11-30) NiseNet — 48.32 (2019-09-24) MaskFormer (ResNet-50) — 55.4 (2021-07-13) Mask2Former (Swin-L, multiscale) — 64.7 (2021-12-02) OneFormer (DiNAT-L, multi-scale) — 64.9 (2022-11-10) AO-SegNet — 76.0 (2023-07-07)
RankModel mIoU PaperCodeYear
1 AO-SegNet 76.0 Interactive Learning of Intrinsic and Extrinsic Properties for All-day Semantic Segmentation BiQiWHU/All-day-CityScapes-segmentation 2023
2 OneFormer (DiNAT-L, multi-scale) 64.9 OneFormer: One Transformer to Rule Universal Image Segmentation huggingface/transformers · SHI-Labs/OneFormer · yangyucheng000/University · +1 2022
3 Mask2Former (Swin-L, multiscale) 64.7 Masked-attention Mask Transformer for Universal Image Segmentation huggingface/transformers · open-mmlab/mmdetection · facebookresearch/Mask2Former · +4 2021
4 MaskFormer (ResNet-50) 55.4 Per-Pixel Classification is Not All You Need for Semantic Segmentation huggingface/transformers · open-mmlab/mmdetection · facebookresearch/MaskFormer 2021
5 NiseNet 48.32 What's There in the Dark sauradip/night_image_semantic_segmentation 2019
6 MRFP+(Ours) Resnet50 44.93 MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation airl-iisc/MRFP 2023
7 SegBlocks-RN50 (t=0.4) 39.7 SegBlocks: Block-Based Dynamic Resolution Networks for Real-Time Segmentation thomasverelst/segblocks-segmentation-pytorch 2020
8 Resnet50 32.93 MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation airl-iisc/MRFP 2023
9 AO-SegNet 76.0 Interactive Learning of Intrinsic and Extrinsic Properties for All-day Semantic Segmentation BiQiWHU/All-day-CityScapes-segmentation 2023
10 OneFormer (DiNAT-L, multi-scale) 64.9 OneFormer: One Transformer to Rule Universal Image Segmentation huggingface/transformers · SHI-Labs/OneFormer · yangyucheng000/University · +1 2022
11 Mask2Former (Swin-L, multiscale) 64.7 Masked-attention Mask Transformer for Universal Image Segmentation huggingface/transformers · open-mmlab/mmdetection · facebookresearch/Mask2Former · +4 2021
12 MaskFormer (ResNet-50) 55.4 Per-Pixel Classification is Not All You Need for Semantic Segmentation huggingface/transformers · open-mmlab/mmdetection · facebookresearch/MaskFormer 2021
13 NiseNet 48.32 What's There in the Dark sauradip/night_image_semantic_segmentation 2019
14 MRFP+(Ours) Resnet50 44.93 MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation airl-iisc/MRFP 2023
15 SegBlocks-RN50 (t=0.4) 39.7 SegBlocks: Block-Based Dynamic Resolution Networks for Real-Time Segmentation thomasverelst/segblocks-segmentation-pytorch 2020
16 Resnet50 32.93 MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation airl-iisc/MRFP 2023
1–16 / 16 페이지당 10 20 50 100