Communication Dans Un Congrès Année : 2025

CATALOG: A Camera Trap Language-guided Contrastive Learning Model

Résumé

Foundation Models (FMs) have been successful in various computer vision tasks like image classification, object detection and image segmentation. However, these tasks remain challenging when these models are tested on datasets with different distributions from the training dataset, a problem known as domain shift. This is especially problematic for recognizing animal species in camera-trap images where we have variability in factors like lighting, camouflage and occlusions. In this paper, we propose the Camera Trap Language-guided Contrastive Learning (CATALOG) model to address these issues. Our approach combines multiple FMs to extract visual and textual features from camera-trap data and uses a contrastive loss function to train the model. We evaluate CATALOG on two benchmark datasets and show that it outperforms previous state-of-theart methods in camera-trap image recognition, especially when the training and testing data have different animal species or come from different geographical areas. Our approach demonstrates the potential of using FMs in combination with multi-modal fusion and contrastive learning for addressing domain shifts in camera-trap image recognition. The code of CATALOG is publicly available at https://github.com/Julian075/CATALOG.

Fichier principal
Vignette du fichier
2412.10624v1.pdf (1.18 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05166701 , version 1 (17-07-2025)

Licence

Identifiants

Citer

Julian Santamaria, Claudia Isaza, Jhony Giraldo. CATALOG: A Camera Trap Language-guided Contrastive Learning Model. 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Feb 2025, Tucson, United States. pp.1197-1206, ⟨10.1109/WACV61041.2025.00124⟩. ⟨hal-05166701⟩
1486 Consultations
242 Téléchargements

Altmetric

Partager

  • More