Cross-Species Animal Re-Identification with Semantic Consistency Learning

• URL: http://arxiv.org/abs/2609.09705v1
• Date: Wed, 09 Sep 2026 04:41:01 GMT
• Title: Cross-Species Animal Re-Identification with Semantic Consistency Learning
• Abstract summary: Generalizable animal Re-Identification (ReID) aims to recognize individual animals across species with diverse morphologies and ecological contexts.<n>Unlike person ReID, animal species often exhibit drastically different anatomical structures and visual patterns, making it difficult to establish shared visual correspondences.<n>We propose Semantic Consistency Learning (SCL), a framework designed to learn representations that remain stable across appearance variations.
• Score: 49.843830441987684
• License: http://creativecommons.org/licenses/by-sa/4.0/
• 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.

Related papers

• DS@GT ARC at AnimalCLEF 2026: Species-Aware Graph Construction for Multi-Species Animal Re-Identification [0.0]
  The DS@GT ARC submission to AnimalCLEF 2026 introduces a multi-species image-clustering system for re-identification.<n>Instead of relying on a single descriptor or nearest-neighbor retrieval, this approach formulates re-identification as species-aware graph construction.
  arXiv  Detail & Related papers  (2026-07-17T18:49:49Z)
• PathAR: Structure-First Autoregressive Synthesis of Multimodal Pathology Images [51.428093790826814]
  We propose pathology Autorgressive modeling (PathAR) to factorize structure and appearance for modality-label-conditioned pathology generation.<n>PathAR stabilizes morphology under heterogeneous modality-specific appearances and enables spatially aligned image-mask pair generation.
  arXiv  Detail & Related papers  (2026-06-01T01:43:48Z)
• MS-CLR: Multi-Skeleton Contrastive Learning for Human Action Recognition [49.91188543847175]
  Multi-Skeleton Contrastive Learning (MS-CLR) is a framework that aligns pose representations across multiple skeleton conventions extracted from the same sequence.<n>MS-CLR consistently improves performance over strong single-skeleton contrastive learning baselines.<n>A multi-skeleton ensemble further boosts performance, setting new state-of-the-art results on both datasets.
  arXiv  Detail & Related papers  (2025-08-20T17:58:03Z)
• DiffPose-Animal: A Language-Conditioned Diffusion Framework for Animal Pose Estimation [1.1708207558288541]
  We introduce DiffPose-Animal, a novel diffusion-based framework for top-down animal pose estimation.<n>Unlike traditional heatmap regression methods, DiffPose-Animal reformulates pose estimation as a denoising process under the generative framework of diffusion models.
  arXiv  Detail & Related papers  (2025-08-12T09:37:09Z)
• CISO: Species Distribution Modeling Conditioned on Incomplete Species Observations [31.010868781061006]
  Species distribution models (SDMs) are widely used to predict species' geographic distributions.<n>CSIS is a deep learning-based method for species distribution modeling Conditioned on Incomplete Species Observations.<n>We demonstrate our approach using three datasets representing different species groups: sOpen for plants, SatBird for birds, and a new dataset, SatButterfly, for butterflies.
  arXiv  Detail & Related papers  (2025-08-08T21:15:12Z)
• BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning [60.80381372245902]
  We find emergent behaviors in biological vision models via large-scale contrastive vision-language training.<n>We train BioCLIP 2 on TreeOfLife-200M to distinguish different species.<n>We identify emergent properties in the learned embedding space of BioCLIP 2.
  arXiv  Detail & Related papers  (2025-05-29T17:48:20Z)
• G2PDiffusion: Cross-Species Genotype-to-Phenotype Prediction via Evolutionary Diffusion [108.94237816552024]
  We propose the first genotype-to-phenotype diffusion model (G2PDiffusion) that generates morphological images from DNA.<n>The model contains three novel components: 1) a MSA retrieval engine that identifies conserved and co-evolutionary patterns; 2) an environment-aware MSA conditional encoder that effectively models complex genotype-environment interactions; and 3) an adaptive phenomic alignment module to improve genotype-phenotype consistency.
  arXiv  Detail & Related papers  (2025-02-07T06:16:31Z)
• An Individual Identity-Driven Framework for Animal Re-Identification [15.381573249551181]
  IndivAID is a framework specifically designed for Animal ReID. It generates image-specific and individual-specific textual descriptions that fully capture the diverse visual concepts of each individual across animal images. Evaluation against state-of-the-art methods across eight benchmark datasets and a real-world Stoat dataset demonstrates IndivAID's effectiveness and applicability.
  arXiv  Detail & Related papers  (2024-10-30T11:34:55Z)
• Transferring Dense Pose to Proximal Animal Classes [83.84439508978126]
  We show that it is possible to transfer the knowledge existing in dense pose recognition for humans, as well as in more general object detectors and segmenters, to the problem of dense pose recognition in other classes. We do this by establishing a DensePose model for the new animal which is also geometrically aligned to humans. We also introduce two benchmark datasets labelled in the manner of DensePose for the class chimpanzee and use them to evaluate our approach.
  arXiv  Detail & Related papers  (2020-02-28T21:43:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.