A contrastive learning approach for individual re-identification in a wild fish population
| Autor: | Ørjan Langøy Olsen, Tonje Knutsen Sørdalen, Morten Goodwin, Ketil Malde, Kristian Muri Knausgård, Kim Tallaksen Halvorsen |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2023 |
| Předmět: |
FOS: Computer and information sciences
Identification Computer Science - Machine Learning Biometric J.3 Computer Science - Artificial Intelligence I.2.6 Computer Vision and Pattern Recognition (cs.CV) I.5.4 Computer Science - Computer Vision and Pattern Recognition Individual Deep learning Siamese network General Medicine I.4.9 Machine Learning (cs.LG) Recognition Fish Artificial Intelligence (cs.AI) Temperate species CNN Embedding |
| Zdroj: | Proceedings of the Northern Lights Deep Learning Workshop; Vol. 4 (2023): Proceedings of the Northern Lights Deep Learning Workshop 2023 |
| ISSN: | 2703-6928 |
| Popis: | In both terrestrial and marine ecology, physical tagging is a frequently used method to study population dynamics and behavior. However, such tagging techniques are increasingly being replaced by individual re-identification using image analysis. This paper introduces a contrastive learning-based model for identifying individuals. The model uses the first parts of the Inception v3 network, supported by a projection head, and we use contrastive learning to find similar or dissimilar image pairs from a collection of uniform photographs. We apply this technique for corkwing wrasse, Symphodus melops, an ecologically and commercially important fish species. Photos are taken during repeated catches of the same individuals from a wild population, where the intervals between individual sightings might range from a few days to several years. Our model achieves a one-shot accuracy of 0.35, a 5-shot accuracy of 0.56, and a 100-shot accuracy of 0.88, on our dataset. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|