What Does Animal Re-Identification Learn? Linear Biological Concepts and Their Origins in Visual Representations

• URL: http://arxiv.org/abs/2609.06020v1
• Date: Sat, 05 Sep 2026 10:46:27 GMT
• Title: What Does Animal Re-Identification Learn? Linear Biological Concepts and Their Origins in Visual Representations
• Abstract summary: We show that sex and age emerge as linear directions that generalize to held-out individuals.<n>We also show that sex direction is causally used by the model, flipping a significant fraction of predictions to the opposite sex.
• Score: 52.11506532642883
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Conservation increasingly relies on camera traps that collect more wildlife imagery than experts can manually analyze, making animal re-identification (Re-ID) essential for monitoring individuals and populations. Yet understanding which cues drive model decisions is challenging for ViT-based Re-ID models, whose metric-learning objectives provide no explicit supervision for biological concepts. We ask whether such models nonetheless organize their representations along biologically meaningful axes. Using a DINOv3 backbone fine-tuned for Western lowland gorilla Re-ID with triplet-margin loss, we find that sex and age emerge as linear directions that generalize to held-out individuals, reaching up to 0.91 AUROC and being recoverable from a single image per individual. Activation steering further shows that the sex direction is causally used by the model, flipping a significant fraction of predictions to the opposite sex. Comparing off-the-shelf and fine-tuned backbones shows that Re-ID training does not create these concepts, but relocates them across the network. Finally, data attribution reveals that the representation we find reflects a graded biological axis, is redundantly encoded across the population and shaped by visually ambiguous individuals. Together, these findings show how interpretability can uncover both the biological structure and failure modes of Re-ID representations, providing a step toward auditable computer vision for wildlife monitoring.

Related papers

• Autonomous UAV Navigation for Individual Wildlife Re-Identification [0.350327094468706]
  We propose an autonomous drone navigation system that actively optimize image capture for downstream re-ID.<n>The system combines YOLOv11 object detection with a DINOv2-based pose to guide real-time flight decisions.<n>We show the approach generalizes to other species with diagnostic surface patterns, including giraffes, tigers, and elephants.
  arXiv  Detail & Related papers  (2026-06-30T14:56:04Z)
• CHIRP dataset: towards long-term, individual-level, behavioral monitoring of bird populations in the wild [2.172490512050822]
  Long-term behavioral monitoring of individual animals is crucial for studying behavioral changes that occur over different time scales.<n>Computer vision methods have proven to benefit biodiversity monitoring, but automated behavior monitoring in wild populations remains challenging.<n>Here, we introduce such a dataset (CHIRP) with a new method (CORVID) for individual re-identification of wild birds.
  arXiv  Detail & Related papers  (2026-03-26T14:57:31Z)
• Wildlife Target Re-Identification Using Self-supervised Learning in Non-Urban Settings [0.0]
  Wildlife re-identification aims to match individuals of the same species across different observations.<n>Current state-of-the-art (SOTA) models rely on class labels to train supervised models for individual classification.<n>This study investigates self-supervised learning Self-Supervised Learning (SSL) for wildlife re-identification.
  arXiv  Detail & Related papers  (2025-07-03T07:56:54Z)
• SD-ReID: View-aware Stable Diffusion for Aerial-Ground Person Re-Identification [74.36139886192495]
  We propose a novel generative framework named SD-ReID for AG-ReID.<n>We first train a ViT-based model to extract person representations along with controllable conditions, including identity and view conditions.<n>We then fine-tune the Stable Diffusion (SD) model to enhance person representations guided by these controllable conditions.
  arXiv  Detail & Related papers  (2025-04-13T12:44:50Z)
• 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)
• When Does Perceptual Alignment Benefit Vision Representations? [76.32336818860965]
  We investigate how aligning vision model representations to human perceptual judgments impacts their usability. We find that aligning models to perceptual judgments yields representations that improve upon the original backbones across many downstream tasks. Our results suggest that injecting an inductive bias about human perceptual knowledge into vision models can contribute to better representations.
  arXiv  Detail & Related papers  (2024-10-14T17:59:58Z)
• PoseBench: Benchmarking the Robustness of Pose Estimation Models under Corruptions [57.871692507044344]
  Pose estimation aims to accurately identify anatomical keypoints in humans and animals using monocular images. Current models are typically trained and tested on clean data, potentially overlooking the corruption during real-world deployment. We introduce PoseBench, a benchmark designed to evaluate the robustness of pose estimation models against real-world corruption.
  arXiv  Detail & Related papers  (2024-06-20T14:40:17Z)
• Addressing the Elephant in the Room: Robust Animal Re-Identification with Unsupervised Part-Based Feature Alignment [44.86310789545717]
  Animal Re-ID is crucial for wildlife conservation, yet it faces unique challenges compared to person Re-ID. This study addresses background biases by proposing a method to systematically remove backgrounds in both training and evaluation phases. Our method achieves superior results on three key animal Re-ID datasets: ATRW, YakReID-103, and ELPephants.
  arXiv  Detail & Related papers  (2024-05-22T16:08:06Z)
• Beyond Tracking: Using Deep Learning to Discover Novel Interactions in Biological Swarms [3.441021278275805]
  We propose training deep network models to predict system-level states directly from generic graphical features from the entire view. Because the resulting predictive models are not based on human-understood predictors, we use explanatory modules. This represents an example of augmented intelligence in behavioral ecology -- knowledge co-creation in a human-AI team.
  arXiv  Detail & Related papers  (2021-08-20T22:50:41Z)
• Fully Unsupervised Person Re-identification viaSelective Contrastive Learning [58.5284246878277]
  Person re-identification (ReID) aims at searching the same identity person among images captured by various cameras. We propose a novel selective contrastive learning framework for unsupervised feature learning. Experimental results demonstrate the superiority of our method in unsupervised person ReID compared with the state-of-the-arts.
  arXiv  Detail & Related papers  (2020-10-15T09:09:23Z)
• Appearance Consensus Driven Self-Supervised Human Mesh Recovery [67.20942777949793]
  We present a self-supervised human mesh recovery framework to infer human pose and shape from monocular images. We achieve state-of-the-art results on the standard model-based 3D pose estimation benchmarks. The resulting colored mesh prediction opens up the usage of our framework for a variety of appearance-related tasks beyond the pose and shape estimation.
  arXiv  Detail & Related papers  (2020-08-04T05:40:39Z)

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.