{"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/medical-image-segmentation-via-cascaded","title":"Medical Image Segmentation via Cascaded Attention Decoding","arxiv_id":null,"date":"2023-01-03","proceeding":"Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023 1","authors":["Md Mostafijur Rahman","Radu Marculescu"],"abstract":"Transformers have shown great promise in medical image segmentation due to their ability to capture long-range dependencies through self-attention. However, they lack the ability to learn the local (contextual) relations among pixels. Previous works try to overcome this problem by embedding convolutional layers either in the encoder or decoder modules of transformers thus ending up sometimes with inconsistent features. To address this issue, we propose a novel attention-based decoder, namely CASCaded Attention DEcoder (CASCADE), which leverages the multiscale features of hierarchical vision transformers. CASCADE consists of i) an attention gate which fuses features with skip connections and ii) a convolutional attention module that enhances the long-range and local context by suppressing background information. We use a multi-stage feature and loss aggregation framework due to their faster convergence and better performance. Our experiments demonstrate that transformers with CASCADE significantly outperform state-of-the-art CNN- and transformer-based approaches, obtaining up to 5.07% and 6.16% improvements in DICE and mIoU scores, respectively. CASCADE opens new ways of designing better attention-based decoders.","url_abs":"https://openaccess.thecvf.com/content/WACV2023/html/Rahman_Medical_Image_Segmentation_via_Cascaded_Attention_Decoding_WACV_2023_paper.html","url_pdf":"https://openaccess.thecvf.com/content/WACV2023/papers/Rahman_Medical_Image_Segmentation_via_Cascaded_Attention_Decoding_WACV_2023_paper.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":"medical-image-segmentation-via-cascaded","repo_url":"https://github.com/SLDGroup/CASCADE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"medical-image-segmentation","task_name":"Medical Image Segmentation"},{"task_slug":"polyp-segmentation","task_name":"Polyp 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/medical-image-segmentation-on-automatic","task":"Medical Image Segmentation","dataset":"Automatic Cardiac Diagnosis Challenge (ACDC)","model":"TransCASCADE","rank_in_archive_order":12,"of":20,"metrics":{"Avg DSC":"91.63"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-segmentation-on-automatic","task":"Medical Image Segmentation","dataset":"Automatic Cardiac Diagnosis Challenge (ACDC)","model":"PVT-CASCADE","rank_in_archive_order":13,"of":20,"metrics":{"Avg DSC":"91.46"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-segmentation-on-cvc-clinicdb","task":"Medical Image Segmentation","dataset":"CVC-ClinicDB","model":"PVT-CASCADE","rank_in_archive_order":16,"of":48,"metrics":{"mIoU":"0.8998","mean Dice":"0.9434"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-segmentation-on-cvc-colondb","task":"Medical Image Segmentation","dataset":"CVC-ColonDB","model":"PVT-CASCADE","rank_in_archive_order":10,"of":25,"metrics":{"mIoU":"0.7453","mean Dice":"0.8254"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-segmentation-on-etis","task":"Medical Image Segmentation","dataset":"ETIS-LARIBPOLYPDB","model":"PVT-CASCADE","rank_in_archive_order":9,"of":25,"metrics":{"mIoU":"0.7258","mean Dice":"0.8007"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-segmentation-on-kvasir-seg","task":"Medical Image Segmentation","dataset":"Kvasir-SEG","model":"PVT-CASCADE","rank_in_archive_order":21,"of":58,"metrics":{"mIoU":"0.8776","mean Dice":"0.9258"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-segmentation-on-miccai-2015-1","task":"Medical Image Segmentation","dataset":"MICCAI 2015 Multi-Atlas Abdomen Labeling Challenge","model":"TransCASCADE","rank_in_archive_order":6,"of":8,"metrics":{"Avg DSC":"82.68","Avg HD":"17.34"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-segmentation-on-miccai-2015-1","task":"Medical Image Segmentation","dataset":"MICCAI 2015 Multi-Atlas Abdomen Labeling Challenge","model":"PVT-CASCADE","rank_in_archive_order":8,"of":8,"metrics":{"Avg DSC":"81.06","Avg HD":"20.23"},"uses_additional_data":false},{"leaderboard":"/sota/polyp-segmentation-on-kvasir-seg","task":"Polyp Segmentation","dataset":"Kvasir-SEG","model":"PVT-CASCADE","rank_in_archive_order":1,"of":8,"metrics":{"mDice":"0.9258","mIoU":"0.8776"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}