构建汽车模型时间演化数据集，支持分类与生成任务的时序适应研究
CaMiT: A Time-Aware Car Model Dataset for Classification and Generation
- 基于2005-2023年190款车模，构建78.7万标注样本+510万无标签样本的数据集
- 提出时间增量学习框架，使模型在跨年测试中准确率提升显著
- 首次融合时间元数据实现时序感知图像生成，输出更符合真实演变规律
AI系统需适应动态视觉环境，尤其在物体外观随时间演化的领域。我们提出车模时间演化数据集CaMiT，涵盖190款汽车（2007–2023），包含78.7万标注样本和510万未标注样本，支持监督与自监督学习。在域内静态预训练可达到与大型通用模型相当性能，且更高效，但跨年测试时准确率下降。为此，我们提出时间增量分类设置——一种包含新增、演化与消失类别的现实持续学习场景。评估两种策略：时间增量预训练（更新主干）与时间增量分类器学习（仅更新最后一层），二者均提升时序鲁棒性。最后，探索利用时间元数据进行时序感知图像生成，获得更真实的结果。CaMiT为细粒度视觉识别与生成中的时序适应研究提供丰富基准。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。