DS@GT ARC at AnimalCLEF 2026: Species-Aware Graph Construction for Multi-Species Animal Re-Identification
Computer Vision and Pattern Recognition
Summary
The authors created a method to recognize individual animals from photos, even when images vary in pose, lighting, or background. They treat this as a problem of grouping images by species and identity using a graph where pictures are connected if they likely show the same animal. Their system uses special image processing, local feature matching, and smart clustering to avoid mistakes where groups get wrongly merged. Tests showed their method works well across different species and ranked fifth in a large competition. The authors highlight that both good visual clues and careful graph-based grouping are needed for reliable animal identification.
Authors
Evan Sinclair Smith, Anthony Miyaguchi, Snigdha Palamari, Danté Evangelista
Abstract
Automated individual animal re-identification is essential for large-scale biodiversity monitoring; however, field imagery complicates separating identity cues from nuisance variation in pose, illumination, background, resolution, and species-specific morphology. The DS@GT ARC submission to AnimalCLEF 2026 introduces a multi-species image-clustering system for re-identifying Eurasian lynx, fire salamanders, loggerhead sea turtles, and Texas horned lizards. Instead of relying on a single descriptor or nearest-neighbor retrieval, this approach formulates re-identification as species-aware graph construction over candidate image pairs. The pipeline integrates tailored preprocessing, global candidate retrieval, LightGlue-based local verification with multiple keypoint families, LightGBM pair scoring, conservative edge admission, and Leiden community detection. This design directly addresses a primary failure mode of clustering-based re-identification: high-scoring false pairs that act as bridge edges and merge distinct individuals through transitive closure. Across species, ablation studies demonstrate that local feature support, foreground-aware preprocessing, and species-specific backbone selection enhance pair evidence, while graph operating points determine the trade-off between fragmentation and over-merging. The selected submission achieved a public ARI of 0.733 and a private ARI of 0.674, ranking fifth among 230 teams. These results indicate that robust wildlife re-identification requires not only strong visual representations but also calibrated integration of global similarity, local identity markings, neighborhood context, and graph-level constraints. The code can be found at https://github.com/dsgt-arc/animalclef-2026.