Hierarchical Re-Classification: Combining Animal Classification Models with Vision Transformers
This work addresses the need for more precise species-level identification in conservation platforms, though it is incremental as it builds on existing models and datasets.
The paper tackled the problem of animal classification models often labeling animals at high taxonomic levels instead of species, by developing a hierarchical re-classification system that refined high-level labels to species-level identification with 96.5% accuracy on a dataset of 4,018 images.
State-of-the-art animal classification models like SpeciesNet provide predictions across thousands of species but use conservative rollup strategies, resulting in many animals labeled at high taxonomic levels rather than species. We present a hierarchical re-classification system for the Animal Detect platform that combines SpeciesNet EfficientNetV2-M predictions with CLIP embeddings and metric learning to refine high-level taxonomic labels toward species-level identification. Our five-stage pipeline (high-confidence acceptance, bird override, centroid building, triplet-loss metric learning, and adaptive cosine-distance scoring) is evaluated on a segment of the LILA BC Desert Lion Conservation dataset (4,018 images, 15,031 detections). After recovering 761 bird detections from "blank" and "animal" labels, we re-classify 456 detections labeled animal, mammal, or blank with 96.5% accuracy, achieving species-level identification for 64.9 percent