Cross-Species Animal Re-Identification with Semantic Consistency Learning

2026-09-09

AI Summary

本文提出语义一致性学习(SCL)框架，通过稳定特征统计和捕捉跨物种的可转移关系结构来解决跨物种动物再识别问题。

Abstract

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.

Problem

• Cross-Species
• Animal Re-Identification
• Semantic Consistency
• Generalization

Innovation

• Semantic Consistency Learning
• Foreground-Background Decoupled Spectral Normalization
• Cross-species Neighborhood Modeling