发表机构
The University of Hong Kong; Shenzhen University; Xiamen University（香港大学; 深圳大学; 厦门大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对医学图像开放世界偏移（长尾、异常、层级分类），提出GBD基准与SCAN方法，通过预测抑制、惊异显著性和互补适应，在保留临床知识的同时提升新颖概念发现。
AI 中文摘要
在真实世界的临床实践中，医学图像面临开放世界的偏移：（i）长尾罕见疾病，（ii）以正常解剖结构为主的细微病变，以及（iii）层级分类体系。然而，大多数开放世界范式假设平坦且平衡的标签空间，未能解决这些生物医学需求。我们引入了广义生物医学发现（GBD）及一个涵盖长尾、异常和分类感知发现的统一基准。我们的关键洞察是，主导的已知模式形成了一个视觉流形，掩盖了细微的新颖性。受专家诊断启发，我们提出了SCAN（惊异诱发的互补适应），它遵循认知启发的感知进程：应用预测抑制以过滤预期规范，触发惊异诱发的显著性以突出意外偏差，并执行互补适应以将这些偏移整合到全局表示中。大量实验表明，SCAN在提升新颖概念发现的同时，总体上保留了已建立的临床知识，并且它能插入现有架构，以更好地导航医学成像中已知-未知的权衡。代码可在以下https URL获取。
英文摘要
In real-world clinical practice, medical images face open-world shifts: (i) long-tailed rare diseases, (ii) subtle lesions dominated by normal anatomy, and (iii) hierarchical taxonomies. Yet most open-world paradigms assume flat, balanced label spaces, leaving these biomedical demands unresolved. We introduce Generalized Biomedicine Discovery (GBD) and a unified benchmark spanning long-tail, anomaly, and taxonomy-aware discovery. Our key insight is that dominant known patterns form a visual manifold that masks subtle novelty. Inspired by expert diagnosis, we propose SCAN (Surprise-evoked Complementary AccommodatioN), which follows a cognition-inspired perceptual progression: it applies predictive suppression to filter expected norms, triggers surprise-evoked salience to highlight unexpected deviations, and performs complementary accommodation to integrate these shifts into global representations. Extensive experiments show that SCAN improves novel concept discovery while generally preserving established clinical knowledge, and it plugs into existing architectures to better navigate the known-unknown trade-off in medical imaging. Code is available at https://github.com/lytang63/generalized-biomedicine-discovery.
CommentsAccepted by **ECCV 2026**
