Abstract
Current object re-identification (ReID) methods train domain-specific models (e.g., for persons or vehicles), which lack generalization and demand costly labeled data for new categories. While self-supervised learning reduces annotation needs by learning instance-wise invariance, it struggles to capture \textit{identity-sensitive} features critical for ReID. This paper proposes Visual In-Context Prompting~(VICP), a novel framework where models trained on seen categories can directly generalize to unseen novel categories using only \textit{in-context examples} as prompts, without requiring parameter adaptation. VICP synergizes LLMs and vision foundation models~(VFM): LLMs infer semantic identity rules from few-shot positive/negative pairs through task-specific prompting, which then guides a VFM (\eg, DINO) to extract ID-discriminative features via \textit{dynamic visual prompts}. By aligning LLM-derived semantic concepts with the VFM's pre-trained prior, VICP enables generalization to novel categories, eliminating the need for dataset-specific retraining. To support evaluation, we introduce ShopID10K, a dataset of 10K object instances from e-commerce platforms, featuring multi-view images and cross-domain testing. Experiments on ShopID10K and diverse ReID benchmarks demonstrate that VICP outperforms baselines by a clear margin on unseen categories. Code is available at this https URL.
Abstract (translated)
当前的对象重识别（ReID）方法训练特定领域的模型（例如针对人员或车辆），这限制了它们的泛化能力，并且对于新类别需要昂贵的标注数据。虽然自我监督学习通过实例级别的不变性学习减少了注释需求，但它难以捕捉对重识别至关重要的“身份敏感”特征。本文提出了视觉上下文提示（VICP）框架，这是一种新型方法，在该框架中，训练好的模型可以直接使用仅有的“在上下文中的示例”作为提示来泛化到未见过的新类别，而无需调整参数。VICP将大型语言模型（LLM）和视觉基础模型（VFM）相结合：LLMs 通过特定任务的提示从少量正负对中推断出语义身份规则，然后指导 VFM（例如 DINO）提取识别特征，借助于“动态视觉提示”。通过将 LLM 推导出来的语义概念与 VFM 预训练的基础模型对齐，VICP 实现了向新类别的泛化，并消除了特定数据集重新训练的需要。为了支持评估，我们引入了一个名为 ShopID10K 的数据集，该数据集包含来自电子商务平台的 10,000 多个对象实例，具有多视角图像和跨域测试功能。在 ShopID10K 和各种 ReID 基准上的实验表明，VICP 在未见过的类别上明显优于基线方法。代码可在以下 URL 获得：[此 https URL]。
URL
https://arxiv.org/abs/2508.21222
