CaMiT: A Time-Aware Car Model Dataset for Classification and Generation
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_ | 1866911224168448000 |
|---|---|
| author | LIN, Frédéric Ambaw, Biruk Abere Popescu, Adrian Ammar, Hejer Audigier, Romaric Borgne, Hervé Le |
| author_facet | LIN, Frédéric Ambaw, Biruk Abere Popescu, Adrian Ammar, Hejer Audigier, Romaric Borgne, Hervé Le |
| contents | AI systems must adapt to evolving visual environments, especially in domains where object appearances change over time. We introduce Car Models in Time (CaMiT), a fine-grained dataset capturing the temporal evolution of car models, a representative class of technological artifacts. CaMiT includes 787K labeled samples of 190 car models (2007-2023) and 5.1M unlabeled samples (2005-2023), supporting both supervised and self-supervised learning. Static pretraining on in-domain data achieves competitive performance with large-scale generalist models while being more resource-efficient, yet accuracy declines when models are tested across years. To address this, we propose a time-incremental classification setting, a realistic continual learning scenario with emerging, evolving, and disappearing classes. We evaluate two strategies: time-incremental pretraining, which updates the backbone, and time-incremental classifier learning, which updates only the final layer, both improving temporal robustness. Finally, we explore time-aware image generation that leverages temporal metadata during training, yielding more realistic outputs. CaMiT offers a rich benchmark for studying temporal adaptation in fine-grained visual recognition and generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_17626 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CaMiT: A Time-Aware Car Model Dataset for Classification and Generation LIN, Frédéric Ambaw, Biruk Abere Popescu, Adrian Ammar, Hejer Audigier, Romaric Borgne, Hervé Le Computer Vision and Pattern Recognition Artificial Intelligence AI systems must adapt to evolving visual environments, especially in domains where object appearances change over time. We introduce Car Models in Time (CaMiT), a fine-grained dataset capturing the temporal evolution of car models, a representative class of technological artifacts. CaMiT includes 787K labeled samples of 190 car models (2007-2023) and 5.1M unlabeled samples (2005-2023), supporting both supervised and self-supervised learning. Static pretraining on in-domain data achieves competitive performance with large-scale generalist models while being more resource-efficient, yet accuracy declines when models are tested across years. To address this, we propose a time-incremental classification setting, a realistic continual learning scenario with emerging, evolving, and disappearing classes. We evaluate two strategies: time-incremental pretraining, which updates the backbone, and time-incremental classifier learning, which updates only the final layer, both improving temporal robustness. Finally, we explore time-aware image generation that leverages temporal metadata during training, yielding more realistic outputs. CaMiT offers a rich benchmark for studying temporal adaptation in fine-grained visual recognition and generation. |
| title | CaMiT: A Time-Aware Car Model Dataset for Classification and Generation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2510.17626 |