Aerial Image Segmentation is a top-down perspective semantic segmentation and has several challenging characteristics such as strong imbalance in the foreground-background distribution, complex background, intra-class heterogeneity, inter-class homogeneity, and tiny objects. To handle these problems, we inherit the advantages of Transformers and propose AerialFormer, which unifies Transformers at the contracting path with lightweight Multi-Dilated Convolutional Neural Networks (MD-CNNs) at the expanding path. Our AerialFormer is designed as a hierarchical structure, in which Transformer encoder outputs multi-scale features and MD-CNNs decoder aggregates information from the multi-scales. Thus, it takes both local and global contexts into consideration to render powerful representations and high-resolution segmentation. We have benchmarked AerialFormer on three common datasets including iSAID, LoveDA, and Potsdam. Comprehensive experiments and extensive ablation studies show that our proposed AerialFormer outperforms previous state-of-the-art methods with remarkable performance. Our source code will be publicly available upon acceptance.
@article{arxiv.2306.06842,
title = {AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation},
author = {Kashu Yamazaki and Taisei Hanyu and Minh Tran and Adrian de Luis and Roy McCann and Haitao Liao and Chase Rainwater and Meredith Adkins and Jackson Cothren and Ngan Le},
journal= {arXiv preprint arXiv:2306.06842},
year = {2023}
}