{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/aerialformer-multi-resolution-transformer-for","title":"AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation","arxiv_id":"2306.06842","date":"2023-06-12","proceeding":null,"authors":["Kashu Yamazaki","Taisei Hanyu","Minh Tran","Adrian de Luis","Roy McCann","Haitao Liao","Chase Rainwater","Meredith Adkins","Jackson Cothren","Ngan Le"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2306.06842v2","url_pdf":"https://arxiv.org/pdf/2306.06842v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"aerialformer-multi-resolution-transformer-for","repo_url":"https://github.com/UARK-AICV/AerialFormer","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-isprs-potsdam","task":"Semantic Segmentation","dataset":"ISPRS Potsdam","model":"AerialFormer-B","rank_in_archive_order":1,"of":20,"metrics":{"Mean F1":"94.1","Mean IoU":"89.1","Overall Accuracy":"93.9"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-loveda","task":"Semantic Segmentation","dataset":"LoveDA","model":"AerialFormer-B","rank_in_archive_order":8,"of":19,"metrics":{"Category mIoU":"54.1"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-isaid","task":"Semantic Segmentation","dataset":"iSAID","model":"AerialFormer-B","rank_in_archive_order":3,"of":19,"metrics":{"mIoU":"69.3"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-isaid","task":"Semantic Segmentation","dataset":"iSAID","model":"AerialFormer-S","rank_in_archive_order":5,"of":19,"metrics":{"mIoU":"68.4"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-isaid","task":"Semantic Segmentation","dataset":"iSAID","model":"AerialFormer-T","rank_in_archive_order":9,"of":19,"metrics":{"mIoU":"67.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.06842","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}