OpenWildlife: Open-Vocabulary Multi-Species Wildlife Detector for Geographically-Diverse Aerial Imagery
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912446360322048 |
|---|---|
| author | Patel, Muhammed Turnes, Javier Noa Hsiao, Jayden Xu, Linlin Clausi, David |
| author_facet | Patel, Muhammed Turnes, Javier Noa Hsiao, Jayden Xu, Linlin Clausi, David |
| contents | We introduce OpenWildlife (OW), an open-vocabulary wildlife detector designed for multi-species identification in diverse aerial imagery. While existing automated methods perform well in specific settings, they often struggle to generalize across different species and environments due to limited taxonomic coverage and rigid model architectures. In contrast, OW leverages language-aware embeddings and a novel adaptation of the Grounding-DINO framework, enabling it to identify species specified through natural language inputs across both terrestrial and marine environments. Trained on 15 datasets, OW outperforms most existing methods, achieving up to \textbf{0.981} mAP50 with fine-tuning and \textbf{0.597} mAP50 on seven datasets featuring novel species. Additionally, we introduce an efficient search algorithm that combines k-nearest neighbors and breadth-first search to prioritize areas where social species are likely to be found. This approach captures over \textbf{95\%} of species while exploring only \textbf{33\%} of the available images. To support reproducibility, we publicly release our source code and dataset splits, establishing OW as a flexible, cost-effective solution for global biodiversity assessments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_19204 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OpenWildlife: Open-Vocabulary Multi-Species Wildlife Detector for Geographically-Diverse Aerial Imagery Patel, Muhammed Turnes, Javier Noa Hsiao, Jayden Xu, Linlin Clausi, David Computer Vision and Pattern Recognition We introduce OpenWildlife (OW), an open-vocabulary wildlife detector designed for multi-species identification in diverse aerial imagery. While existing automated methods perform well in specific settings, they often struggle to generalize across different species and environments due to limited taxonomic coverage and rigid model architectures. In contrast, OW leverages language-aware embeddings and a novel adaptation of the Grounding-DINO framework, enabling it to identify species specified through natural language inputs across both terrestrial and marine environments. Trained on 15 datasets, OW outperforms most existing methods, achieving up to \textbf{0.981} mAP50 with fine-tuning and \textbf{0.597} mAP50 on seven datasets featuring novel species. Additionally, we introduce an efficient search algorithm that combines k-nearest neighbors and breadth-first search to prioritize areas where social species are likely to be found. This approach captures over \textbf{95\%} of species while exploring only \textbf{33\%} of the available images. To support reproducibility, we publicly release our source code and dataset splits, establishing OW as a flexible, cost-effective solution for global biodiversity assessments. |
| title | OpenWildlife: Open-Vocabulary Multi-Species Wildlife Detector for Geographically-Diverse Aerial Imagery |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.19204 |