# DS@GT AnimalCLEF: Triplet Learning over ViT Manifolds with Nearest Neighbor Classification for Animal Re-identification

arXiv: https://arxiv.org/abs/2509.12353 · HTML: https://mlsanity.com/paper/2509.12353/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 20 references that are in the map.
- First posted on arXiv 15 Sep 2025.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Matryoshka Representation Learning](https://mlsanity.com/paper/2205.13147/) (2022)
- [Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualization](https://mlsanity.com/paper/2012.04456/) (2020)
- [WildlifeDatasets: An open-source toolkit for animal re-identification](https://mlsanity.com/paper/2311.09118/) (2023)
- [Towards Self-Supervision for Video Identification of Individual Holstein-Friesian Cattle: The Cows2021 Dataset](https://mlsanity.com/paper/2105.01938/) (2021)
- [An Individual Identity-Driven Framework for Animal Re-Identification](https://mlsanity.com/paper/2410.22927/) (2024)
- [Transfer Learning with Self-Supervised Vision Transformers for Snake Identification](https://mlsanity.com/paper/2407.06178/) (2024)

## Built on by (most cited first, 2 of 2)

- [DS@GT ARC at AnimalCLEF 2026: Species-Aware Graph Construction for Multi-Species Animal Re-Identification](https://mlsanity.com/paper/2607.16453/) (2026)
- [Decoupled Pipeline with Proposal Reranking and Score Fusion for Positive-Unlabeled Marine Species Detection](https://mlsanity.com/paper/2607.18700/) (2026)

## Abstract (arXiv)

This paper details the DS@GT team's entry for the AnimalCLEF 2025 re-identification challenge. Our key finding is that the effectiveness of post-hoc metric learning is highly contingent on the initial quality and domain-specificity of the backbone embeddings. We compare a general-purpose model (DINOv2) with a domain-specific model (MegaDescriptor) as a backbone. A K-Nearest Neighbor classifier with robust thresholding then identifies known individuals or flags new ones. While a triplet-learning projection head improved the performance of the specialized MegaDescriptor model by 0.13 points, it yielded minimal gains (0.03) for the general-purpose DINOv2 on averaged BAKS and BAUS. We demonstrate that the general-purpose manifold is more difficult to reshape for fine-grained tasks, as evidenced by stagnant validation loss and qualitative visualizations. This work highlights the critical limitations of refining general-purpose features for specialized, limited-data re-ID tasks and underscores the importance of domain-specific pre-training. The implementation for this work is publicly available at github.com/dsgt-arc/animalclef-2025.