# Multispecies Animal Re-ID Using a Large Community-Curated Dataset

arXiv: https://arxiv.org/abs/2412.05602 · HTML: https://mlsanity.com/paper/2412.05602/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 38 references that are in the map.
- First posted on arXiv 7 Dec 2024.

## Builds on (most cited first, 1 of 1)

- [Wildbook: Crowdsourcing, computer vision, and data science for conservation](https://mlsanity.com/paper/1710.08880/) (2017)

## Built on by (most cited first, 18 of 18)

- [Unsupervised Pelage Pattern Unwrapping for Animal Re-identification](https://mlsanity.com/paper/2506.15369/) (2025)
- [GorillaWatch: An Automated System for In-the-Wild Gorilla Re-Identification and Population Monitoring](https://mlsanity.com/paper/2512.07776/) (2025)
- [Pairwise Matching of Intermediate Representations for Fine-grained Explainability](https://mlsanity.com/paper/2503.22881/) (2025)
- [Active Learning for Animal Re-Identification with Ambiguity-Aware Sampling](https://mlsanity.com/paper/2511.06658/) (2025)
- [Finer-Personalization Rank: Fine-Grained Retrieval Examines Identity Preservation for Personalized Generation](https://mlsanity.com/paper/2512.19026/) (2025)
- [Wildlife Target Re-Identification Using Self-supervised Learning in Non-Urban Settings](https://mlsanity.com/paper/2507.02403/) (2025)
- [Weakly supervised framework for wildlife detection and counting in challenging Arctic environments: a case study on caribou (Rangifer tarandus)](https://mlsanity.com/paper/2601.18891/) (2026)
- [Degradation-based augmented training for robust individual animal re-identification](https://mlsanity.com/paper/2603.04163/) (2026)
- [ID-Sim: An Identity-Focused Similarity Metric](https://mlsanity.com/paper/2604.05039/) (2026)
- [Are We Recognizing the Jaguar or Its Background? A Diagnostic Framework for Jaguar Re-Identification](https://mlsanity.com/paper/2604.09690/) (2026)
- [DS@GT ARC at AnimalCLEF 2026: Species-Aware Graph Construction for Multi-Species Animal Re-Identification](https://mlsanity.com/paper/2607.16453/) (2026)
- [INQUIRE-Search: Interactive Discovery in Large-Scale Biodiversity Databases](https://mlsanity.com/paper/2511.15656/) (2025)
- [From Visual to Multimodal: Systematic Ablation of Encoders and Fusion Strategies in Animal Identification](https://mlsanity.com/paper/2603.02270/) (2026)
- [Centering Ecological Goals in Automated Identification of Individual Animals](https://mlsanity.com/paper/2604.20626/) (2026)
- [Spotted: Location-informed Reidentification of Hyenas and Leopards in Camera Trap Surveys](https://mlsanity.com/paper/2607.00804/) (2026)
- [Calibrated Similarity and Graph Clustering for Open-Set Animal Re-Identification](https://mlsanity.com/paper/2608.02469/) (2026)
- [Cross-Species Animal Re-Identification with Semantic Consistency Learning](https://mlsanity.com/paper/2609.09705/) (2026)
- [WildMatch: Weakly Supervised Image Matcher Adaptation for Wildlife Re-Identification](https://mlsanity.com/paper/2610.07384/) (2026)

## Abstract (arXiv)

Recent work has established the ecological importance of developing algorithms for identifying animals individually from images. Typically, a separate algorithm is trained for each species, a natural step but one that creates significant barriers to wide-spread use: (1) each effort is expensive, requiring data collection, data curation, and model training, deployment, and maintenance, (2) there is little training data for many species, and (3) commonalities in appearance across species are not exploited. We propose an alternative approach focused on training multi-species individual identification (re-id) models. 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. Our model employs an EfficientNetV2 backbone and a sub-center ArcFace loss function with dynamic margins. We evaluate the performance of this multispecies model in several ways. Most notably, we demonstrate that it consistently outperforms models trained separately on each species, achieving an average gain of 12.5% in top-1 accuracy. Furthermore, the model demonstrates strong zero-shot performance and fine-tuning capabilities for new species with limited training data, enabling effective curation of new species through both incremental addition of data to the training set and fine-tuning without the original data. Additionally, our model surpasses the recent MegaDescriptor on unseen species, averaging an 19.2% top-1 improvement per species and showing gains across all 33 species tested. The fully-featured code repository is publicly available on GitHub, and the feature extractor model can be accessed on HuggingFace for seamless integration with wildlife re-identification pipelines. The model is already in production use for 60+ species in a large-scale wildlife monitoring system.