Metraipolis › archive › dc_229e92f14540

Semantic Prior-Guided Incomplete Cross-Modal Retrieval with Noisy Labels — arXiv:2611.06113

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.06113
License (as archived)
CC0-1.0
Archived
2026-11-05T18:29:56.670Z
SHA-256 of the archived text
e97384d18dbd8890b034d846b4c615e5ad9064386340950332eca15a9ef73b57
Stable URL of this page
https://metraipolis.com/documento/dc_229e92f14540

How to cite

Semantic Prior-Guided Incomplete Cross-Modal Retrieval with Noisy Labels — arXiv:2611.06113 — arXiv (en), https://arxiv.org/abs/2611.06113 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_229e92f14540 (Metraipolis archive dc_229e92f14540, sha256 e97384d18dbd8890b034d846b4c615e5ad9064386340950332eca15a9ef73b57)
BibTeX
@misc{dc229e92f14540,
  title = {Semantic Prior-Guided Incomplete Cross-Modal Retrieval with Noisy Labels — arXiv:2611.06113},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06113},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_229e92f14540; sha256 e97384d18dbd8890b034d846b4c615e5ad9064386340950332eca15a9ef73b57},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06113. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Cross-modal retrieval (CMR) aims to bridge the semantic gaps between modalities by learning shared representations. Unfortunately, due to the dynamism and inconsistencies in real-world data acquisition, multimodal datasets frequently encounter severe modality incompleteness. Existing incomplete CMR methods adhere to a label-driven paradigm, relying heavily on categorical annotations as the semantic benchmark. However, label noise is difficult to avoid and often coexists with modality incompleteness. To address this challenge, we propose a novel semantic prior-guided framework for incomplete cross-modal retrieval with noisy labels, termed SPIRN. Specifically, SPIRN uses fixed semantic priors as a consistent reference for robust representation learning, noisy-label handling, and missing-modality completion. Based on this reference, Semantic Priors Guidance (SPG) establishes a stable category-level semantic space, Quality-aware Robust Learning (QRL) dynamically evaluates sample quality to distinguish clean samples from noisy ones and handles noise via reverse learning, Prior-guided Global Label Calibration (PGLC) rectifies corrupted annotations for refined supervision, and Confidence-driven Selective Imputation (CSI) recovers missing modalities from a cross-modal memory bank while filtering unreliable imputations with an increasing threshold. To the best of our knowledge, this is the first framework to jointly tackle the dual challenges of modality incompleteness and label noise in the CMR community. Extensive experiments on four widely used benchmark datasets demonstrate that SPIRN outperforms 11 state-of-the-art methods in various scenarios involving both missing modalities and noisy labels.

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/2611.06113 — 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 2026-11-05T18:19:49.051Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).