发表机构
School of Computer Science, Wuhan University（武汉大学计算机学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出语义一致性学习（SCL）框架，通过前景-背景解耦谱归一化和跨物种邻域建模，在11个数据集上实现跨物种动物重识别的最优性能。
AI 中文摘要
可泛化的动物重识别（ReID）旨在识别具有不同形态和生态环境的跨物种个体动物。与不同域共享相似身体结构的人物重识别不同，动物物种通常表现出截然不同的解剖结构和视觉模式，这使得建立共享的视觉对应关系变得困难。因此，跨物种学习到的表示往往形成碎片化的嵌入空间，严重限制了跨物种泛化能力。为解决这一挑战，我们提出了语义一致性学习（SCL），这是一个旨在学习在表观变化下保持稳定、同时保留跨物种共享语义结构的表示的框架。SCL由两个互补组件组成。前景-背景解耦谱归一化（FDSNorm）通过以区域感知方式抑制环境引起的风格变化来稳定特征统计，而跨物种邻域建模（CNM）通过动态特征邻域捕获跨物种的可迁移关系结构。在11个公开动物重识别数据集上的大量实验表明，SCL在多种跨物种评估协议下始终优于最先进的方法，并能有效泛化到先前未见过的物种和生态域。代码可在该https URL获取。
英文摘要
Generalizable animal Re-Identification (ReID) aims to recognize individual animals across species with diverse morphologies and ecological contexts. Unlike person ReID, where different domains share similar body structures, animal species often exhibit drastically different anatomical structures and visual patterns, making it difficult to establish shared visual correspondences. As a result, representations learned across species tend to form fragmented embedding spaces, which severely limits cross-species generalization. To address this challenge, we propose Semantic Consistency Learning (SCL), a framework designed to learn representations that remain stable across appearance variations while preserving semantic structures shared across species. SCL consists of two complementary components. Foreground-Background Decoupled Spectral Normalization (FDSNorm) stabilizes feature statistics by suppressing environment-induced style variations in a region-aware manner, while Cross-species Neighborhood Modeling (CNM) captures transferable relational structures across species through dynamic feature neighborhoods. Extensive experiments on 11 public animal ReID datasets demonstrate that SCL consistently outperforms state-of-the-art methods under multiple cross-species evaluation protocols and generalizes effectively to previously unseen species and ecological domains. Code is available at https://github.com/Kemalau/ECCV-26-SCL.
CommentsAccepted to ECCV 2026. 18 pages, 5 figures
