Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2406.13002 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917698850521088 |
|---|---|
| author | Rogers, Mitchell Knowles, Kobe Gendron, Gaël Heidari, Shahrokh Valdez, David Arturo Soriano Azhar, Mihailo O'Leary, Padriac Eyre, Simon Witbrock, Michael Delmas, Patrice |
| author_facet | Rogers, Mitchell Knowles, Kobe Gendron, Gaël Heidari, Shahrokh Valdez, David Arturo Soriano Azhar, Mihailo O'Leary, Padriac Eyre, Simon Witbrock, Michael Delmas, Patrice |
| contents | Deep learning approaches for animal re-identification have had a major impact on conservation, significantly reducing the time required for many downstream tasks, such as well-being monitoring. We propose a method called Recurrence over Video Frames (RoVF), which uses a recurrent head based on the Perceiver architecture to iteratively construct an embedding from a video clip. RoVF is trained using triplet loss based on the co-occurrence of individuals in the video frames, where the individual IDs are unavailable. We tested this method and various models based on the DINOv2 transformer architecture on a dataset of meerkats collected at the Wellington Zoo. Our method achieves a top-1 re-identification accuracy of $49\%$, which is higher than that of the best DINOv2 model ($42\%$). We found that the model can match observations of individuals where humans cannot, and our model (RoVF) performs better than the comparisons with minimal fine-tuning. In future work, we plan to improve these models by using pre-text tasks, apply them to animal behaviour classification, and perform a hyperparameter search to optimise the models further. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_13002 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Recurrence over Video Frames (RoVF) for the Re-identification of Meerkats Rogers, Mitchell Knowles, Kobe Gendron, Gaël Heidari, Shahrokh Valdez, David Arturo Soriano Azhar, Mihailo O'Leary, Padriac Eyre, Simon Witbrock, Michael Delmas, Patrice Computer Vision and Pattern Recognition Deep learning approaches for animal re-identification have had a major impact on conservation, significantly reducing the time required for many downstream tasks, such as well-being monitoring. We propose a method called Recurrence over Video Frames (RoVF), which uses a recurrent head based on the Perceiver architecture to iteratively construct an embedding from a video clip. RoVF is trained using triplet loss based on the co-occurrence of individuals in the video frames, where the individual IDs are unavailable. We tested this method and various models based on the DINOv2 transformer architecture on a dataset of meerkats collected at the Wellington Zoo. Our method achieves a top-1 re-identification accuracy of $49\%$, which is higher than that of the best DINOv2 model ($42\%$). We found that the model can match observations of individuals where humans cannot, and our model (RoVF) performs better than the comparisons with minimal fine-tuning. In future work, we plan to improve these models by using pre-text tasks, apply them to animal behaviour classification, and perform a hyperparameter search to optimise the models further. |
| title | Recurrence over Video Frames (RoVF) for the Re-identification of Meerkats |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.13002 |