Active Learning for Animal Re-Identification with Ambiguity-Aware Sampling

• URL: http://arxiv.org/abs/2511.06658v2
• Date: Wed, 12 Nov 2025 01:50:04 GMT
• Title: Active Learning for Animal Re-Identification with Ambiguity-Aware Sampling
• Authors: Depanshu Sani, Mehar Khurana, Saket Anand,
• Abstract summary: We introduce a novel AL Re-ID framework that leverages complementary clustering methods to uncover and target structurally ambiguous regions.<n>We show that our approach consistently outperforms existing foundational, USL and AL baselines.<n>Specifically, we report an average improvement of 10.49%, 11.19% and 3.99% (mAP) on 13 wildlife datasets over foundational, USL and AL methods, respectively.
• Score: 2.1290878226779877
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Animal Re-ID has recently gained substantial attention in the AI research community due to its high impact on biodiversity monitoring and unique research challenges arising from environmental factors. The subtle distinguishing patterns, handling new species and the inherent open-set nature make the problem even harder. To address these complexities, foundation models trained on labeled, large-scale and multi-species animal Re-ID datasets have recently been introduced to enable zero-shot Re-ID. However, our benchmarking reveals significant gaps in their zero-shot Re-ID performance for both known and unknown species. While this highlights the need for collecting labeled data in new domains, exhaustive annotation for Re-ID is laborious and requires domain expertise. Our analyses show that existing unsupervised (USL) and AL Re-ID methods underperform for animal Re-ID. To address these limitations, we introduce a novel AL Re-ID framework that leverages complementary clustering methods to uncover and target structurally ambiguous regions in the embedding space for mining pairs of samples that are both informative and broadly representative. Oracle feedback on these pairs, in the form of must-link and cannot-link constraints, facilitates a simple annotation interface, which naturally integrates with existing USL methods through our proposed constrained clustering refinement algorithm. Through extensive experiments, we demonstrate that, by utilizing only 0.033% of all annotations, our approach consistently outperforms existing foundational, USL and AL baselines. Specifically, we report an average improvement of 10.49%, 11.19% and 3.99% (mAP) on 13 wildlife datasets over foundational, USL and AL methods, respectively, while attaining state-of-the-art performance on each dataset. Furthermore, we also show an improvement of 11.09%, 8.2% and 2.06% for unknown individuals in an open-world setting.

Related papers

• From Visual to Multimodal: Systematic Ablation of Encoders and Fusion Strategies in Animal Identification [35.71275089934349]
  This study introduces a multimodal verification framework that enhances visual features with semantic identity priors derived from synthetic textual descriptions.<n>We constructed a massive training corpus of 1.9 million photographs covering 695,091unique animals to support this investigation.
  arXiv  Detail & Related papers  (2026-02-28T21:27:38Z)
• Automated Re-Identification of Holstein-Friesian Cattle in Dense Crowds [2.3843187053931456]
  We propose a new detect-segment-identify pipeline that leverages the Open-Vocabulary Weight-free Localisation and the Segment Anything models.<n>Our methodology overcomes detection breakdown in dense animal groupings, resulting in a 98.93% accuracy.<n>We show that unsupervised contrastive learning can build on this to yield 94.82% Re-ID accuracy on our test data.
  arXiv  Detail & Related papers  (2026-02-17T19:25:50Z)
• CFReID: Continual Few-shot Person Re-Identification [127.60234742605832]
  Lifelong ReID has been proposed to learn and accumulate knowledge across multiple domains incrementally.<n>LReID models need to be trained on large-scale labeled data for each unseen domain, which are typically inaccessible due to privacy and cost concerns.<n>We propose Continual Few-shot ReID, which requires models to be incrementally trained using few-shot data and tested on all seen domains.
  arXiv  Detail & Related papers  (2025-03-24T09:17:05Z)
• Multispecies Animal Re-ID Using a Large Community-Curated Dataset [0.19418036471925312]
  We construct a dataset that includes 49 species, 37K individual animals, and 225K images, using this data to train a single embedding network for all species.<n>Our model consistently outperforms models trained separately on each species, achieving an average gain of 12.5% in top-1 accuracy.<n>The model is already in production use for 60+ species in a large-scale wildlife monitoring system.
  arXiv  Detail & Related papers  (2024-12-07T09:56:33Z)
• OpenAnimals: Revisiting Person Re-Identification for Animals Towards Better Generalization [10.176567936487364]
  We conduct a study by revisiting several state-of-the-art person re-identification methods, including BoT, AGW, SBS, and MGN. We evaluate their effectiveness on animal re-identification benchmarks such as HyenaID, LeopardID, SeaTurtleID, and WhaleSharkID. Our findings reveal that while some techniques well, many do not generalize, underscoring the significant differences between the two tasks. We propose ARBase, a strong textbfBase model tailored for textbfAnimal textbfRe-
  arXiv  Detail & Related papers  (2024-09-30T20:07:14Z)
• WildlifeReID-10k: Wildlife re-identification dataset with 10k individual animals [0.0]
  This paper introduces WildlifeReID-10k, a new large-scale re-identification benchmark with more than 10k animal identities of around 33 species across more than 140k images.<n>WildlifeReID-10k covers diverse animal species and poses significant challenges for SoTA methods.<n>The dataset and benchmark are publicly available on Kaggle, along with strong baselines for both closed-set and open-set evaluation.
  arXiv  Detail & Related papers  (2024-06-13T15:15:07Z)
• Contrastive Multiple Instance Learning for Weakly Supervised Person ReID [50.04900262181093]
  We introduce Contrastive Multiple Instance Learning (CMIL), a novel framework tailored for more effective weakly supervised ReID. CMIL distinguishes itself by requiring only a single model and no pseudo labels while leveraging contrastive losses. We release the WL-MUDD dataset, an extension of the MUDD dataset featuring naturally occurring weak labels from the real-world application at PerformancePhoto.co.
  arXiv  Detail & Related papers  (2024-02-12T14:48:31Z)
• Recognize Any Regions [55.76437190434433]
  RegionSpot integrates position-aware localization knowledge from a localization foundation model with semantic information from a ViL model.<n>Experiments in open-world object recognition show that our RegionSpot achieves significant performance gain over prior alternatives.
  arXiv  Detail & Related papers  (2023-11-02T16:31:49Z)
• Generalizable Re-Identification from Videos with Cycle Association [60.920036335996414]
  We propose Cycle Association (CycAs) as a scalable self-supervised learning method for re-ID with low training complexity. We construct a large-scale unlabeled re-ID dataset named LMP-video, tailored for the proposed method. CycAs learns re-ID features by enforcing cycle consistency of instance association between temporally successive video frame pairs.
  arXiv  Detail & Related papers  (2022-11-07T16:21:57Z)
• Gait Recognition in the Wild: A Large-scale Benchmark and NAS-based Baseline [95.88825497452716]
  Gait benchmarks empower the research community to train and evaluate high-performance gait recognition systems. GREW is the first large-scale dataset for gait recognition in the wild. SPOSGait is the first NAS-based gait recognition model.
  arXiv  Detail & Related papers  (2022-05-05T14:57:39Z)
• Unsupervised Domain Adaptation in Person re-ID via k-Reciprocal Clustering and Large-Scale Heterogeneous Environment Synthesis [76.46004354572956]
  We introduce an unsupervised domain adaptation approach for person re-identification. Experimental results show that the proposed ktCUDA and SHRED approach achieves an average improvement of +5.7 mAP in re-identification performance.
  arXiv  Detail & Related papers  (2020-01-14T17:43:52Z)

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.