{"ID":2896051,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.07602","arxiv_id":"2507.07602","title":"Advancing Medical Image Segmentation via Self-supervised Instance-adaptive Prototype Learning","abstract":"Medical Image Segmentation (MIS) plays a crucial role in medical therapy planning and robot navigation. Prototype learning methods in MIS focus on generating segmentation masks through pixel-to-prototype comparison. However, current approaches often overlook sample diversity by using a fixed prototype per semantic class and neglect intra-class variation within each input. In this paper, we propose to generate instance-adaptive prototypes for MIS, which integrates a common prototype proposal (CPP) capturing common visual patterns and an instance-specific prototype proposal (IPP) tailored to each input. To further account for the intra-class variation, we propose to guide the IPP generation by re-weighting the intermediate feature map according to their confidence scores. These confidence scores are hierarchically generated using a transformer decoder. Additionally we introduce a novel self-supervised filtering strategy to prioritize the foreground pixels during the training of the transformer decoder. Extensive experiments demonstrate favorable performance of our method.","short_abstract":"Medical Image Segmentation (MIS) plays a crucial role in medical therapy planning and robot navigation. Prototype learning methods in MIS focus on generating segmentation masks through pixel-to-prototype comparison. However, current approaches often overlook sample diversity by using a fixed prototype per semantic clas...","url_abs":"https://arxiv.org/abs/2507.07602","url_pdf":"https://arxiv.org/pdf/2507.07602v1","authors":"[\"Guoyan Liang\",\"Qin Zhou\",\"Jingyuan Chen\",\"Zhe Wang\",\"Chang Yao\"]","published":"2025-07-10T10:04:03Z","proceeding":"stat.ME","tasks":"[\"stat.ME\",\"eess.IV\"]","methods":"[\"Transformer\"]","has_code":false}