Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2606.01981 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917554903056384 |
|---|---|
| author | Mabrouk, Anis Yassine Ben Tadros, Antoine von Gioi, Rafael Grompone Facciolo, Gabriele Davy, Axel Verschae, Rodrigo |
| author_facet | Mabrouk, Anis Yassine Ben Tadros, Antoine von Gioi, Rafael Grompone Facciolo, Gabriele Davy, Axel Verschae, Rodrigo |
| contents | Vehicle re-identification focuses on retrieving images of the same vehicle from a gallery given a query image. Upon closer inspection of commonly used datasets, we observe that vehicles with few visual differences-e.g., the same make, model, and color-appear in both the training and test sets. As a result, methods that effectively memorize the training data tend to perform well on these test sets but struggle to generalize to other datasets. In this paper, we address this issue by proposing a novel evaluation approach that more effectively measures generalization capability to unseen vehicle types. To further study generalization performance, we also propose splitting the evaluation based on view, allowing us to differentiate the effect of viewpoint robustness from that of same-view re-identification. Our findings reveal that most state-of-the-art methods struggle with unseen vehicle types, and that their robustness to viewpoint changes and attention to detail are limited to vehicle types seen during training. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_01981 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Generalization Limits in Vehicle Re-Identification Mabrouk, Anis Yassine Ben Tadros, Antoine von Gioi, Rafael Grompone Facciolo, Gabriele Davy, Axel Verschae, Rodrigo Computer Vision and Pattern Recognition Vehicle re-identification focuses on retrieving images of the same vehicle from a gallery given a query image. Upon closer inspection of commonly used datasets, we observe that vehicles with few visual differences-e.g., the same make, model, and color-appear in both the training and test sets. As a result, methods that effectively memorize the training data tend to perform well on these test sets but struggle to generalize to other datasets. In this paper, we address this issue by proposing a novel evaluation approach that more effectively measures generalization capability to unseen vehicle types. To further study generalization performance, we also propose splitting the evaluation based on view, allowing us to differentiate the effect of viewpoint robustness from that of same-view re-identification. Our findings reveal that most state-of-the-art methods struggle with unseen vehicle types, and that their robustness to viewpoint changes and attention to detail are limited to vehicle types seen during training. |
| title | Generalization Limits in Vehicle Re-Identification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2606.01981 |