paper-with-me

Semantic Segmentation 벤치마크

Semantic Segmentation on LoveDA

40개 결과 · ⬇ CSV · JSON

Category mIoU

49.79 51.38 52.97 54.57 56.16 2021-09 2026-09 UNetFormer — 52.4 (2021-09-18) UNetFormer — 52.4 (2021-09-18) HRNetw32 — 49.79 (2021-10-17) HRNetw32 — 49.79 (2021-10-17) ViTAE-B + RVSA-UperNet — 52.44 (2022-08-08) ViT-B + RVSA-UperNet — 51.95 (2022-08-08) ViTAE-B + RVSA-UperNet — 52.44 (2022-08-08) ViT-B + RVSA-UperNet — 51.95 (2022-08-08) LSKNet-S — 54.0 (2023-03-16) LSKNet-T — 53.2 (2023-03-16) LSKNet-S — 54.0 (2023-03-16) LSKNet-T — 53.2 (2023-03-16) ViT-G12X4 — 54.4 (2023-04-11) ViT-G12X4 — 54.4 (2023-04-11) Hi-ResNet — 52.6 (2023-05-22) Hi-ResNet — 52.6 (2023-05-22) AerialFormer-B — 54.1 (2023-06-12) AerialFormer-B — 54.1 (2023-06-12) MAE+MTP(ViT-L+RVSA) — 54.17 (2024-03-20) IMP+MTP(InternImage-XL) — 54.17 (2024-03-20) MAE+MTP(ViT-B+RVSA) — 52.39 (2024-03-20) MAE+MTP(ViT-L+RVSA) — 54.17 (2024-03-20) IMP+MTP(InternImage-XL) — 54.17 (2024-03-20) MAE+MTP(ViT-B+RVSA) — 52.39 (2024-03-20) U-Net (MaxViT-S) — 56.16 (2024-06-08) U-Net (MaxViT-S) — 56.16 (2024-06-08) SelectiveMAE+ViT-L — 54.31 (2024-06-17) SelectiveMAE+ViT-L — 54.31 (2024-06-17) LOGCAN++ — 53.35 (2024-06-24) LOGCAN++ — 53.35 (2024-06-24) SFA-Net — 54.9 (2024-09-03) SFA-Net — 54.9 (2024-09-03) DecoupleNet D2 — 53.1 (2024-09-23) DecoupleNet D2 — 53.1 (2024-09-23) LWGANet L2 — 53.6 (2025-01-17) LWGANet L2 — 53.6 (2025-01-17) D2LS — 55.3 (2025-03-09) D2LS — 55.3 (2025-03-09) Terrace — 52.19 (2025-08-06) TEFormer — 53.55 (2025-08-08) UNetFormer — 52.4 (2021-09-18) ViTAE-B + RVSA-UperNet — 52.44 (2022-08-08) LSKNet-S — 54.0 (2023-03-16) ViT-G12X4 — 54.4 (2023-04-11) U-Net (MaxViT-S) — 56.16 (2024-06-08)
RankModel Category mIoU Extra Training Data PaperCodeYear
1 U-Net (MaxViT-S) 56.16 U-Net Ensemble for Enhanced Semantic Segmentation in Remote Sensing Imagery 2024
2 D2LS 55.3 Dynamic Dictionary Learning for Remote Sensing Image Segmentation XavierJiezou/D2LS 2025
3 SFA-Net 54.9 SFA-Net: Semantic Feature Adjustment Network for Remote Sensing Image Segmentation j2jeong/priv 2024
4 ViT-G12X4 54.4 ✓ A Billion-scale Foundation Model for Remote Sensing Images 2023
5 SelectiveMAE+ViT-L 54.31 Scaling Efficient Masked Image Modeling on Large Remote Sensing Dataset Fengxiang23/SelectiveMAE 2024
6 MAE+MTP(ViT-L+RVSA) 54.17 MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining vitae-transformer/mtp · cuzyoung/crossearth 2024
6 IMP+MTP(InternImage-XL) 54.17 MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining vitae-transformer/mtp · cuzyoung/crossearth 2024
8 AerialFormer-B 54.1 AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation UARK-AICV/AerialFormer 2023
9 LSKNet-S 54.0 Large Selective Kernel Network for Remote Sensing Object Detection zcablii/Large-Selective-Kernel-Network 2023
10 LWGANet L2 53.6 LWGANet: A Lightweight Group Attention Backbone for Remote Sensing Visual Tasks lwcver/lwganet 2025
11 TEFormer 자동 추출 53.55 TEFormer: Texture-Aware and Edge-Guided Transformer for Semantic Segmentation of Urban Remote Sensing Images 2025
12 LOGCAN++ 53.35 LOGCAN++: Adaptive Local-global class-aware network for semantic segmentation of remote sensing imagery xwmaxwma/rssegmentation 2024
13 LSKNet-T 53.2 Large Selective Kernel Network for Remote Sensing Object Detection zcablii/Large-Selective-Kernel-Network 2023
14 DecoupleNet D2 53.1 DecoupleNet: A Lightweight Backbone Network With Efficient Feature Decoupling for Remote Sensing Visual Tasks lwCVer/DecoupleNet 2024
15 Hi-ResNet 52.6 Hi-ResNet: Edge Detail Enhancement for High-Resolution Remote Sensing Segmentation 2023
16 ViTAE-B + RVSA-UperNet 52.44 Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model vitae-transformer/vitae-transformer-remote-sensing · vitae-transformer/remote-sensing-rvsa 2022
17 UNetFormer 52.40 UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery WangLibo1995/GeoSeg 2021
18 MAE+MTP(ViT-B+RVSA) 52.39 MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining vitae-transformer/mtp · cuzyoung/crossearth 2024
19 Terrace 자동 추출 52.19 TNet: Terrace Convolutional Decoder Network for Remote Sensing Image Semantic Segmentation 2025
20 ViT-B + RVSA-UperNet 51.95 Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model vitae-transformer/vitae-transformer-remote-sensing · vitae-transformer/remote-sensing-rvsa 2022
1–20 / 40 다음 → 페이지당 10 20 50 100