A large-scale climate-aware satellite image dataset for domain adaptive land-cover semantic segmentation

Abstract

A few well-annotated datasets for land-cover semantic segmentation have recently been introduced to advance the field of earth observation technologies. However, these datasets overlook the significant diversity among geographic areas with different climates, which can greatly impact and diversify land cover. Consequently, this leads to a domain gap in remote sensing images and severe performance degradation of the segmentation models. To enhance land-cover semantic segmentation with improved generalization ability, we conducted the first investigation into the impact of climate on this task. In this paper, we present a unique large-scale Climate-Aware Satellite Images Dataset (CASID) specifically designed for domain adaptive land-cover semantic segmentation. It consists of 980 satellite images with a size of 5000 x 5000 pixels, collected from 30 different regions around Asia, covering over 24,500 square kilometers. These images are gathered from four distinct climate zones, namely temperate monsoon, subtropical monsoon, tropical monsoon, and tropical rainforest. It includes four sub-datasets/domains, each representing one of the aforementioned climate zones. This characteristic makes CASID the first climate-aware land-cover semantic segmentation dataset with multiple domains. Additionally, we provide a comprehensive analysis of the samples from the four climate zones, emphasizing differences in global image features, image texture, category distribution, spectral value, and object shape. These analyses offer valuable insights for subsequent research in this field. Moreover, we conduct extensive experiments to evaluate the latest semantic segmentation and unsupervised domain adaptation methods on the CASID dataset. These results serve as a robust baseline for future research endeavors. Our dataset will be made publicly available at https://github.com/Linwei-Chen/CASID.

References in corpus (17)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Decoupled Weight Decay Regularization
• LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation
• UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery
• DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images
• Land-Cover Classification with High-Resolution Remote Sensing Images Using Transferable Deep Models
• SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
• SpaceNet: A Remote Sensing Dataset and Challenge Series
• Land cover mapping at very high resolution with rotation equivariant CNNs: towards small yet accurate models
• Learning Aerial Image Segmentation from Online Maps
• R${}^2$-CNN: Fast Tiny Object Detection in Large-Scale Remote Sensing Images
• An Attention-Fused Network for Semantic Segmentation of Very-High-Resolution Remote Sensing Imagery
• Aerial Imagery for Roof Segmentation: A Large-Scale Dataset towards Automatic Mapping of Buildings
• Instance Segmentation in the Dark
• Affinity Space Adaptation for Semantic Segmentation Across Domains
• Birds of A Feather Flock Together: Category-Divergence Guidance for Domain Adaptive Segmentation
• Hybrid supervised instance segmentation by learning label noise suppression