Metraipolis › archive › dc_4ecb956cb4da
VLM-as-a-Judge for Person Re-Identification — arXiv:2611.03027
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.03027
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:42:44.800Z
- SHA-256 of the archived text
8993561e9a925d6b0c4baa7b4af62e434747fdba19bd3e849b24ba120c6e9a6f- Stable URL of this page
https://metraipolis.com/documento/dc_4ecb956cb4da
How to cite
VLM-as-a-Judge for Person Re-Identification — arXiv:2611.03027 — arXiv (en), https://arxiv.org/abs/2611.03027 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4ecb956cb4da (Metraipolis archive dc_4ecb956cb4da, sha256 8993561e9a925d6b0c4baa7b4af62e434747fdba19bd3e849b24ba120c6e9a6f)
BibTeX
@misc{dc4ecb956cb4da,
title = {VLM-as-a-Judge for Person Re-Identification — arXiv:2611.03027},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.03027},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4ecb956cb4da; sha256 8993561e9a925d6b0c4baa7b4af62e434747fdba19bd3e849b24ba120c6e9a6f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03027. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Cloth-changing person re-identification (CC-ReID) is still very challenging, and no method clearly dominates: methods that lead on one benchmark collapse on the others, because they rest on different identity cues. We show that a general-purpose vision-language model (VLM), used zero-shot as a judge for reranking a short candidate list, beats the expert retrieval models it reranks by a wide and consistent margin. On the four scenarios of CHIRLA, a long-term CC-ReID benchmark that no publicly released Re-ID model is trained on, reranking the candidates of two frozen experts raises rank-1 on every scenario, by 12.9 points on average over the best expert and 9.4 over the best naive ensemble of the two, with no component fine-tuned on the target data. Merging both experts' shortlists matches or beats reranking the stronger expert's shortlist alone, at lower cost. Introducing a VLM does, however, come at a cost: almost all of the pipeline's FLOPs are spent on it. We therefore borrow a criterion from ensembling and invoke the VLM judge only where the two experts disagree at rank 1. This threshold-free gate removes 40% of the calls, and a comparable share of total compute, with no significant drop in rank-1, trading 1.8 to 3.8 points of mAP. Judging remains the dominant cost, but on a benchmark where dedicated experts stall, we find a frozen general-purpose model to be the strongest judge of identity. The code is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.03027 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T11:06:37.610Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).