paper-with-me

Semantic Segmentation 벤치마크

Semantic Segmentation on ImageNet-S

40개 결과 · ⬇ CSV · JSON

mIoU (val)

21 31.55 42.1 52.65 63.2 2021-06 2026-09 PASS (ResNet-50 D16, 224x224, LUSS) — 21.6 (2021-06-06) PASS (ResNet-50 D32, 224x224, LUSS) — 21.0 (2021-06-06) PASS (ResNet-50 D16, 224x224, LUSS) — 21.6 (2021-06-06) PASS (ResNet-50 D32, 224x224, LUSS) — 21.0 (2021-06-06) MAE (ViT-B/16, 224x224, SSL+FT, mmseg) — 61.6 (2021-11-11) MAE (ViT-B/16, 224x224, SSL+FT) — 61.0 (2021-11-11) MAE (ViT-B/16, 224x224, SSL, mmseg) — 40.0 (2021-11-11) MAE (ViT-B/16, 224x224, SSL) — 38.3 (2021-11-11) MAE (ViT-B/16, 224x224, SSL+FT, mmseg) — 61.6 (2021-11-11) MAE (ViT-B/16, 224x224, SSL+FT) — 61.0 (2021-11-11) MAE (ViT-B/16, 224x224, SSL, mmseg) — 40.0 (2021-11-11) MAE (ViT-B/16, 224x224, SSL) — 38.3 (2021-11-11) ConvNext-Tiny (P4, 224x224, SUP) — 48.7 (2022-01-10) ConvNext-Tiny (P4, 224x224, SUP) — 48.7 (2022-01-10) SERE (ViT-B/16, 100ep, 224x224, SSL+FT) — 63.0 (2022-06-10) SERE (ViT-S/16, 100ep, 224x224, SSL+FT, mmseg) — 59.4 (2022-06-10) SERE (ViT-S/16, 100ep, 224x224, SSL+FT) — 58.9 (2022-06-10) SERE (ViT-B/16, 100ep, 224x224, SSL) — 48.6 (2022-06-10) SERE (ViT-S/16, 100ep, 224x224, SSL, mmseg) — 41.0 (2022-06-10) SERE (ViT-S/16, 100ep, 224x224, SSL) — 41.0 (2022-06-10) SERE (ViT-B/16, 100ep, 224x224, SSL+FT) — 63.0 (2022-06-10) SERE (ViT-S/16, 100ep, 224x224, SSL+FT, mmseg) — 59.4 (2022-06-10) SERE (ViT-S/16, 100ep, 224x224, SSL+FT) — 58.9 (2022-06-10) SERE (ViT-B/16, 100ep, 224x224, SSL) — 48.6 (2022-06-10) SERE (ViT-S/16, 100ep, 224x224, SSL, mmseg) — 41.0 (2022-06-10) SERE (ViT-S/16, 100ep, 224x224, SSL) — 41.0 (2022-06-10) RF-ConvNext-Tiny (rfmerge, P4, 224x224, SUP) — 51.3 (2022-06-14) RF-ConvNext-Tiny (rfmultiple, P4, 224x224, SUP) — 50.8 (2022-06-14) RF-ConvNext-Tiny (rfsingle, P4, 224x224, SUP) — 50.7 (2022-06-14) RF-ConvNext-Tiny (rfmerge, P4, 224x224, SUP) — 51.3 (2022-06-14) RF-ConvNext-Tiny (rfmultiple, P4, 224x224, SUP) — 50.8 (2022-06-14) RF-ConvNext-Tiny (rfsingle, P4, 224x224, SUP) — 50.7 (2022-06-14) TEC (ViT-B/16, 224x224, SSL+FT, mmseg) — 63.2 (2022-10-20) TEC (ViT-B/16, 224x224, SSL+FT) — 62.0 (2022-10-20) TEC (ViT-B/16, 224x224, SSL, mmseg) — 46.1 (2022-10-20) TEC (ViT-B/16, 224x224, SSL) — 42.9 (2022-10-20) TEC (ViT-B/16, 224x224, SSL+FT, mmseg) — 63.2 (2022-10-20) TEC (ViT-B/16, 224x224, SSL+FT) — 62.0 (2022-10-20) TEC (ViT-B/16, 224x224, SSL, mmseg) — 46.1 (2022-10-20) TEC (ViT-B/16, 224x224, SSL) — 42.9 (2022-10-20) PASS (ResNet-50 D16, 224x224, LUSS) — 21.6 (2021-06-06) MAE (ViT-B/16, 224x224, SSL+FT, mmseg) — 61.6 (2021-11-11) SERE (ViT-B/16, 100ep, 224x224, SSL+FT) — 63.0 (2022-06-10) TEC (ViT-B/16, 224x224, SSL+FT, mmseg) — 63.2 (2022-10-20)
RankModel mIoU (val)mIoU (test) PaperCodeYear
1 TEC (ViT-B/16, 224x224, SSL+FT, mmseg) 63.262.5 Towards Sustainable Self-supervised Learning sail-sg/tec 2022
2 SERE (ViT-B/16, 100ep, 224x224, SSL+FT) 63.063.3 SERE: Exploring Feature Self-relation for Self-supervised Transformer MCG-NKU/SERE 2022
3 TEC (ViT-B/16, 224x224, SSL+FT) 62.0– Towards Sustainable Self-supervised Learning sail-sg/tec 2022
4 MAE (ViT-B/16, 224x224, SSL+FT, mmseg) 61.661.2 Masked Autoencoders Are Scalable Vision Learners facebookresearch/mae · lightly-ai/lightly · open-mmlab/mmselfsup · +55 2021
5 MAE (ViT-B/16, 224x224, SSL+FT) 61.060.2 Masked Autoencoders Are Scalable Vision Learners facebookresearch/mae · lightly-ai/lightly · open-mmlab/mmselfsup · +55 2021
6 SERE (ViT-S/16, 100ep, 224x224, SSL+FT, mmseg) 59.459.0 SERE: Exploring Feature Self-relation for Self-supervised Transformer MCG-NKU/SERE 2022
7 SERE (ViT-S/16, 100ep, 224x224, SSL+FT) 58.957.8 SERE: Exploring Feature Self-relation for Self-supervised Transformer MCG-NKU/SERE 2022
8 RF-ConvNext-Tiny (rfmerge, P4, 224x224, SUP) 51.351.1 RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks ShangHua-Gao/G2L-search · ShangHua-Gao/RFNext 2022
9 RF-ConvNext-Tiny (rfmultiple, P4, 224x224, SUP) 50.850.5 RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks ShangHua-Gao/G2L-search · ShangHua-Gao/RFNext 2022
10 RF-ConvNext-Tiny (rfsingle, P4, 224x224, SUP) 50.750.5 RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks ShangHua-Gao/G2L-search · ShangHua-Gao/RFNext 2022
11 ConvNext-Tiny (P4, 224x224, SUP) 48.748.8 A ConvNet for the 2020s keras-team/keras · rwightman/pytorch-image-models · pytorch/vision · +51 2022
12 SERE (ViT-B/16, 100ep, 224x224, SSL) 48.648.2 SERE: Exploring Feature Self-relation for Self-supervised Transformer MCG-NKU/SERE 2022
13 TEC (ViT-B/16, 224x224, SSL, mmseg) 46.146.0 Towards Sustainable Self-supervised Learning sail-sg/tec 2022
14 TEC (ViT-B/16, 224x224, SSL) 42.9– Towards Sustainable Self-supervised Learning sail-sg/tec 2022
15 SERE (ViT-S/16, 100ep, 224x224, SSL, mmseg) 41.040.5 SERE: Exploring Feature Self-relation for Self-supervised Transformer MCG-NKU/SERE 2022
15 SERE (ViT-S/16, 100ep, 224x224, SSL) 41.040.2 SERE: Exploring Feature Self-relation for Self-supervised Transformer MCG-NKU/SERE 2022
17 MAE (ViT-B/16, 224x224, SSL, mmseg) 40.040.3 Masked Autoencoders Are Scalable Vision Learners facebookresearch/mae · lightly-ai/lightly · open-mmlab/mmselfsup · +55 2021
18 MAE (ViT-B/16, 224x224, SSL) 38.337.0 Masked Autoencoders Are Scalable Vision Learners facebookresearch/mae · lightly-ai/lightly · open-mmlab/mmselfsup · +55 2021
19 PASS (ResNet-50 D16, 224x224, LUSS) 21.620.8 Large-scale Unsupervised Semantic Segmentation LUSSeg/ImageNet-S · LUSSeg/PASS · LUSSeg/ImageNetSegModel 2021
20 PASS (ResNet-50 D32, 224x224, LUSS) 21.020.3 Large-scale Unsupervised Semantic Segmentation LUSSeg/ImageNet-S · LUSSeg/PASS · LUSSeg/ImageNetSegModel 2021
21 TEC (ViT-B/16, 224x224, SSL+FT, mmseg) 63.262.5 Towards Sustainable Self-supervised Learning sail-sg/tec 2022
22 SERE (ViT-B/16, 100ep, 224x224, SSL+FT) 63.063.3 SERE: Exploring Feature Self-relation for Self-supervised Transformer MCG-NKU/SERE 2022
23 TEC (ViT-B/16, 224x224, SSL+FT) 62.0– Towards Sustainable Self-supervised Learning sail-sg/tec 2022
24 MAE (ViT-B/16, 224x224, SSL+FT, mmseg) 61.661.2 Masked Autoencoders Are Scalable Vision Learners facebookresearch/mae · lightly-ai/lightly · open-mmlab/mmselfsup · +55 2021
25 MAE (ViT-B/16, 224x224, SSL+FT) 61.060.2 Masked Autoencoders Are Scalable Vision Learners facebookresearch/mae · lightly-ai/lightly · open-mmlab/mmselfsup · +55 2021
26 SERE (ViT-S/16, 100ep, 224x224, SSL+FT, mmseg) 59.459.0 SERE: Exploring Feature Self-relation for Self-supervised Transformer MCG-NKU/SERE 2022
27 SERE (ViT-S/16, 100ep, 224x224, SSL+FT) 58.957.8 SERE: Exploring Feature Self-relation for Self-supervised Transformer MCG-NKU/SERE 2022
28 RF-ConvNext-Tiny (rfmerge, P4, 224x224, SUP) 51.351.1 RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks ShangHua-Gao/G2L-search · ShangHua-Gao/RFNext 2022
29 RF-ConvNext-Tiny (rfmultiple, P4, 224x224, SUP) 50.850.5 RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks ShangHua-Gao/G2L-search · ShangHua-Gao/RFNext 2022
30 RF-ConvNext-Tiny (rfsingle, P4, 224x224, SUP) 50.750.5 RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks ShangHua-Gao/G2L-search · ShangHua-Gao/RFNext 2022
31 ConvNext-Tiny (P4, 224x224, SUP) 48.748.8 A ConvNet for the 2020s keras-team/keras · rwightman/pytorch-image-models · pytorch/vision · +51 2022
32 SERE (ViT-B/16, 100ep, 224x224, SSL) 48.648.2 SERE: Exploring Feature Self-relation for Self-supervised Transformer MCG-NKU/SERE 2022
33 TEC (ViT-B/16, 224x224, SSL, mmseg) 46.146.0 Towards Sustainable Self-supervised Learning sail-sg/tec 2022
34 TEC (ViT-B/16, 224x224, SSL) 42.9– Towards Sustainable Self-supervised Learning sail-sg/tec 2022
35 SERE (ViT-S/16, 100ep, 224x224, SSL, mmseg) 41.040.5 SERE: Exploring Feature Self-relation for Self-supervised Transformer MCG-NKU/SERE 2022
35 SERE (ViT-S/16, 100ep, 224x224, SSL) 41.040.2 SERE: Exploring Feature Self-relation for Self-supervised Transformer MCG-NKU/SERE 2022
37 MAE (ViT-B/16, 224x224, SSL, mmseg) 40.040.3 Masked Autoencoders Are Scalable Vision Learners facebookresearch/mae · lightly-ai/lightly · open-mmlab/mmselfsup · +55 2021
38 MAE (ViT-B/16, 224x224, SSL) 38.337.0 Masked Autoencoders Are Scalable Vision Learners facebookresearch/mae · lightly-ai/lightly · open-mmlab/mmselfsup · +55 2021
39 PASS (ResNet-50 D16, 224x224, LUSS) 21.620.8 Large-scale Unsupervised Semantic Segmentation LUSSeg/ImageNet-S · LUSSeg/PASS · LUSSeg/ImageNetSegModel 2021
40 PASS (ResNet-50 D32, 224x224, LUSS) 21.020.3 Large-scale Unsupervised Semantic Segmentation LUSSeg/ImageNet-S · LUSSeg/PASS · LUSSeg/ImageNetSegModel 2021
1–40 / 40 페이지당 10 20 50 100