解决监控中车辆颜色识别的长尾分布问题，提升罕见颜色识别效果。
Revisiting Vehicle Color Recognition in Long-Tailed Surveillance Scenarios
- 用文本/图像条件生成合成数据增强少数类样本
- 达到94.6%微平均准确率和79.7%宏平均准确率
- 适合关注真实场景下长尾识别与数据增强的研究者
车辆颜色识别在监控系统中是重要的身份线索，尤其在车牌因分辨率低、遮挡、运动模糊或光照差而无法辨识时。然而，现实中的车辆颜色分布严重不均衡，整体准确率难以反映对稀有但关键颜色的识别性能。本文基于UFPR-VeSV这一具有挑战性的真实监控数据集，全面研究了极端类别不平衡下的车辆颜色识别问题。通过两种现成的生成策略——使用RunDiffusion/JuggernautXL进行文本条件图像生成，以及利用Gemini 2.0 Flash实现图像条件颜色编辑——构建合成数据。将这些数据与现代视觉表示、损失重加权、学习率调度、颜色安全增强、前景感知预处理及集成融合相结合。最佳方法取得94.6%微平均准确率和79.7%宏平均准确率，较近期文献提升8.2个百分点。人工误差分析表明，许多残余错误在人类标注者眼中也存在视觉模糊性，揭示了在无约束监控图像中依赖颜色识别的实际局限性。生成图像与源代码已公开于https://github.com/viniciusorru/vcr-synthetic。
原文摘要 · Abstract (English)
Vehicle color recognition is an important cue for vehicle identification in surveillance systems, especially when license plates are illegible due to low resolution, occlusion, motion blur, or poor illumination. However, real-world vehicle color distributions are highly imbalanced, making overall accuracy insufficient to assess performance on rare but operationally relevant colors. This paper presents a comprehensive study of vehicle color recognition under severe class imbalance using UFPR-VeSV, a challenging real-world surveillance dataset. We investigate synthetic minority-class augmentation through two off-the-shelf generative strategies: text-conditioned image generation with RunDiffusion/JuggernautXL and image-conditioned color editing with Gemini 2.0 Flash. The curated synthetic data are combined with modern visual representations, loss reweighting, learning-rate scheduling, color-safe augmentation, foreground-aware preprocessing, and ensemble fusion. The bestperforming approach achieves 94.6% micro accuracy and 79.7% macro accuracy, improving macro accuracy by 8.2 percentage points over recent literature. A manual error analysis further shows that many remaining failures are visually ambiguous even for human annotators, highlighting the practical limits of color-based vehicle identification in unconstrained surveillance imagery. The generated images and source code are publicly available at https://github.com/viniciusorru/vcr-synthetic
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。