LoveDA

Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation

Dataset Information
Modalities
Images
Languages
English
Introduced
2021
License
CC BY-NC-SA 4.0
Homepage
Official Website
Contents

Overview

  1. 5987 high spatial resolution (0.3 m) remote sensing images from Nanjing, Changzhou, and Wuhan
  2. Focus on different geographical environments between Urban and Rural
  3. Advance both semantic segmentation and domain adaptation tasks
  4. Three considerable challenges:
    • Multi-scale objects
    • Complex background samples
    • Inconsistent class distributions

Two contests are held on the Codalab:
LoveDA Semantic Segmentation Challenge, LoveDA Unsupervised Domain Adaptation Challenge

Variants: LoveDA

Associated Benchmarks

This dataset is used in 1 benchmark:

Recent Benchmark Submissions

Task Model Paper Date
Semantic Segmentation D2LS Dynamic Dictionary Learning for Remote … 2025-03-09
Semantic Segmentation LWGANet L2 LWGANet: A Lightweight Group Attention … 2025-01-17
Semantic Segmentation LOGCAN++ LOGCAN++: Adaptive Local-global class-aware network … 2024-06-24
Semantic Segmentation SelectiveMAE+ViT-L Scaling Efficient Masked Image Modeling … 2024-06-17
Semantic Segmentation MAE+MTP(ViT-L+RVSA) MTP: Advancing Remote Sensing Foundation … 2024-03-20
Semantic Segmentation IMP+MTP(InternImage-XL) MTP: Advancing Remote Sensing Foundation … 2024-03-20
Semantic Segmentation MAE+MTP(ViT-B+RVSA) MTP: Advancing Remote Sensing Foundation … 2024-03-20
Semantic Segmentation AerialFormer-B AerialFormer: Multi-resolution Transformer for Aerial … 2023-06-12
Semantic Segmentation Hi-ResNet Hi-ResNet: Edge Detail Enhancement for … 2023-05-22
Semantic Segmentation ViT-G12X4 A Billion-scale Foundation Model for … 2023-04-11
Semantic Segmentation LSKNet-S Large Selective Kernel Network for … 2023-03-16
Semantic Segmentation LSKNet-T Large Selective Kernel Network for … 2023-03-16
Semantic Segmentation ViT-B + RVSA-UperNet Advancing Plain Vision Transformer Towards … 2022-08-08
Semantic Segmentation ViTAE-B + RVSA-UperNet Advancing Plain Vision Transformer Towards … 2022-08-08
Semantic Segmentation HRNetw32 LoveDA: A Remote Sensing Land-Cover … 2021-10-17
Semantic Segmentation UNetFormer UNetFormer: A UNet-like Transformer for … 2021-09-18

Research Papers

Recent papers with results on this dataset:

External Links: