paper-with-me

Semantic Segmentation 벤치마크

Semantic Segmentation on SynPASS

12개 결과 · ⬇ CSV · JSON

mIoU

21.3 25.77 30.23 34.69 39.16 2018-02 2026-11 DeepLabv3+ — 29.66 (2018-02-07) DeepLabv3+ — 29.66 (2018-02-07) Fast-SCNN — 21.3 (2019-02-12) Fast-SCNN — 21.3 (2019-02-12) PVT — 32.68 (2021-02-24) PVT — 32.68 (2021-02-24) SegFomrer — 37.24 (2021-05-31) SegFomrer — 37.24 (2021-05-31) Trans4PASS — 38.57 (2022-03-02) Trans4PASS — 38.57 (2022-03-02) Trans4PASS+ — 39.16 (2022-07-25) Trans4PASS+ — 39.16 (2022-07-25) DeepLabv3+ — 29.66 (2018-02-07) PVT — 32.68 (2021-02-24) SegFomrer — 37.24 (2021-05-31) Trans4PASS — 38.57 (2022-03-02) Trans4PASS+ — 39.16 (2022-07-25)
RankModel mIoU PaperCodeYear
1 Trans4PASS+ 39.16% Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation jamycheung/trans4pass 2022
2 Trans4PASS 38.57% Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation jamycheung/trans4pass 2022
3 SegFomrer 37.24% SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers huggingface/transformers · VikParuchuri/surya · PaddlePaddle/PaddleSeg · +25 2021
4 PVT 32.68% Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions open-mmlab/mmdetection · open-mmlab/mmpose · whai362/PVT · +8 2021
5 DeepLabv3+ 29.66% Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation tensorflow/models · tensorflow/models · open-mmlab/mmsegmentation · +75 2018
6 Fast-SCNN 21.30% Fast-SCNN: Fast Semantic Segmentation Network open-mmlab/mmsegmentation · PaddlePaddle/PaddleSeg · osmr/imgclsmob · +21 2019
7 Trans4PASS+ 39.16% Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation jamycheung/trans4pass 2022
8 Trans4PASS 38.57% Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation jamycheung/trans4pass 2022
9 SegFomrer 37.24% SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers huggingface/transformers · VikParuchuri/surya · PaddlePaddle/PaddleSeg · +25 2021
10 PVT 32.68% Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions open-mmlab/mmdetection · open-mmlab/mmpose · whai362/PVT · +8 2021
11 DeepLabv3+ 29.66% Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation tensorflow/models · tensorflow/models · open-mmlab/mmsegmentation · +75 2018
12 Fast-SCNN 21.30% Fast-SCNN: Fast Semantic Segmentation Network open-mmlab/mmsegmentation · PaddlePaddle/PaddleSeg · osmr/imgclsmob · +21 2019
1–12 / 12 페이지당 10 20 50 100