Metraipolis › archive › dc_766530aaaacf

Semantic Modality Compensation for Unsupervised Visible-Infrared Person Re-identification under Unpaired Settings — arXiv:2609.34294

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.34294
License (as archived): CC0-1.0
Archived: 2026-10-07T23:52:02.701Z
SHA-256 of the archived text: f9a4d822a6bcef21ff576a766a98564e546081a07eaba3ccf4c700b031a0711e
Stable URL of this page: https://metraipolis.com/documento/dc_766530aaaacf

How to cite

Semantic Modality Compensation for Unsupervised Visible-Infrared Person Re-identification under Unpaired Settings — arXiv:2609.34294 — arXiv (en), https://arxiv.org/abs/2609.34294 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_766530aaaacf (Metraipolis archive dc_766530aaaacf, sha256 f9a4d822a6bcef21ff576a766a98564e546081a07eaba3ccf4c700b031a0711e)

BibTeX

@misc{dc766530aaaacf,
  title = {Semantic Modality Compensation for Unsupervised Visible-Infrared Person Re-identification under Unpaired Settings — arXiv:2609.34294},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34294},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_766530aaaacf; sha256 f9a4d822a6bcef21ff576a766a98564e546081a07eaba3ccf4c700b031a0711e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34294. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Unsupervised visible-infrared person re-identification (USL-VI-ReID) learns person representations that can be compared across modalities without identity annotations. In the unpaired setting, however, identity correspondences between modalities are often incomplete, leaving many identities without an observed counterpart in the other modality. Existing unpaired methods bridge this gap by generating or mapping features for the other modality, mainly by exploiting the statistics of visual features without explicitly separating content that is discriminative for identity from style that is specific to modality. Consequently, the generated features may distort identity cues or inherit bias from the source modality, undermining the reliability of supervision across modalities. We formulate unpaired learning across modalities as a semantic compensation problem and propose Semantic Modality Compensation (SMC), a framework based on prompt composition that decouples identity semantics from modality style within a shared visual semantic space. SMC first constructs a discriminative ReID space through augmented dual contrastive learning, yielding pseudo labels, cluster prototypes, and memory banks for each modality. It then learns visible and infrared modality prompts in the CLIP semantic space and maps clusters obtained from pseudo labels to identity semantic tokens. For each cluster lacking a reliable match in the other modality, SMC combines its identity token with the prompt for the target modality to synthesize a semantic counterpart in the missing modality. The synthesized counterpart is then projected back into the ReID space and injected into a compensation memory through confidence gating. Extensive experiments under both paired and unpaired settings demonstrate that SMC consistently outperforms state-of-the-art methods, with particularly large gains when identity mismatch is severe.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.34294 — 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 2026-10-07T23:29:27.339Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).