{"ID":2877376,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.21222","arxiv_id":"2508.21222","title":"Generalizable Object Re-Identification via Visual In-Context Prompting","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 https://github.com/Hzzone/VICP.","short_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{identit...","url_abs":"https://arxiv.org/abs/2508.21222","url_pdf":"https://arxiv.org/pdf/2508.21222v1","authors":"[\"Zhizhong Huang\",\"Xiaoming Liu\"]","published":"2025-08-28T21:24:06Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Large Language Model\"]","has_code":false,"code_links":[{"ID":610373,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2877376,"paper_url":"https://arxiv.org/abs/2508.21222","paper_title":"Generalizable Object Re-Identification via Visual In-Context Prompting","repo_url":"https://github.com/Hzzone/VICP","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}