{"ID":2846449,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.01143","arxiv_id":"2511.01143","title":"MicroAUNet: Boundary-Enhanced Multi-scale Fusion with Knowledge Distillation for Colonoscopy Polyp Image Segmentation","abstract":"Early and accurate segmentation of colorectal polyps is critical for reducing colorectal cancer mortality, which has been extensively explored by academia and industry. However, current deep learning-based polyp segmentation models either compromise clinical decision-making by providing ambiguous polyp margins in segmentation outputs or rely on heavy architectures with high computational complexity, resulting in insufficient inference speeds for real-time colorectal endoscopic applications. To address this problem, we propose MicroAUNet, a light-weighted attention-based segmentation network that combines depthwise-separable dilated convolutions with a single-path, parameter-shared channel-spatial attention block to strengthen multi-scale boundary features. On the basis of it, a progressive two-stage knowledge-distillation scheme is introduced to transfer semantic and boundary cues from a high-capacity teacher. Extensive experiments on benchmarks also demonstrate the state-of-the-art accuracy under extremely low model complexity, indicating that MicroAUNet is suitable for real-time clinical polyp segmentation. The code is publicly available at https://github.com/JeremyXSC/MicroAUNet.","short_abstract":"Early and accurate segmentation of colorectal polyps is critical for reducing colorectal cancer mortality, which has been extensively explored by academia and industry. However, current deep learning-based polyp segmentation models either compromise clinical decision-making by providing ambiguous polyp margins in segme...","url_abs":"https://arxiv.org/abs/2511.01143","url_pdf":"https://arxiv.org/pdf/2511.01143v1","authors":"[\"Ziyi Wang\",\"Yuanmei Zhang\",\"Dorna Esrafilzadeh\",\"Ali R. Jalili\",\"Suncheng Xiang\"]","published":"2025-11-03T01:43:34Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[]","has_code":false,"code_links":[{"ID":607432,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2846449,"paper_url":"https://arxiv.org/abs/2511.01143","paper_title":"MicroAUNet: Boundary-Enhanced Multi-scale Fusion with Knowledge Distillation for Colonoscopy Polyp Image Segmentation","repo_url":"https://github.com/JeremyXSC/MicroAUNet","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}