CaMiT: A Time-Aware Car Model Dataset for Classification and Generation

TL;DR

CaMiT is a comprehensive dataset capturing the temporal evolution of car models from 2005 to 2023, enabling research on temporal adaptation in classification and generation tasks.

Contribution

The paper introduces CaMiT, a large-scale time-aware car model dataset, and proposes methods for temporal classification and generation to improve model robustness over time.

Findings

Static in-domain pretraining is resource-efficient but less accurate across years.

Time-incremental training strategies improve temporal robustness.

Time-aware generation produces more realistic images with temporal metadata.

Abstract

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.