EUVIMEDEUVIMED entdecken
Crossref

Semantic Contrast for Domain-Robust Underwater Image Quality Assessment

Jingchun Zhou, Chunjiang Liu, Qiuping Jiang, Xianping Fu, Junhui Hou, Xuelong Li

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-06 · 48 (6) · 6279-6296

DOI: 10.1109/tpami.2026.3654426 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-06. Verfasst von Jingchun Zhou und 5 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 68 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Zhejiang Province, Liaoning Provincial Science and Technology Plan Joint Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Underwater image quality assessment (UIQA) is hindered by complex degradation and domain shifts across aquatic environments. Existing no-reference IQA methods rely on costly and subjective mean opinion scores (MOS), which limit their generalization to unseen domains. To overcome these challenges, we propose SCUIA, an unsupervised UIQA framework leveraging semantic contrastive learning for quality prediction without human annotations. Specifically, we introduce a vision-language contrastive learning strategy that aligns image features with textual embeddings in a unified semantic space, capturing implicit degradation-quality correlations. We further enhance quality discrimination with a hierarchical contrastive learning mechanism that combines image-specific statistical priors and semantic prompts. A triplet-based inter-group contrastive loss explicitly models relative quality relationships. To tackle cross-domain variations, we develop an unsupervised domain adaptation module that uses local statistical features to guide CLIP fine-tuning to disentangle domain-invariant quality representations from domain-specific noise. This enables zero-shot cross-domain quality prediction without labeled data. Extensive experiments on public UIQA benchmarks demonstrate significant improvements over existing methods, highlighting superior generalization and domain adaptability.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Zhejiang Province
  • Liaoning Provincial Science and Technology Plan Joint Program
  • Natural Science Foundation - General Program
  • Fundamental Research Funds for the Central Universities
  • Fundamental Research Funds of the Liaoning Provincial Department of Education
  • Hong Kong Research Grants Council

Zitieren

APA

Zhou, J., Liu, C., Jiang, Q., Fu, X., Hou, J., & Li, X. (2026). Semantic Contrast for Domain-Robust Underwater Image Quality Assessment. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(6), 6279-6296. https://doi.org/10.1109/tpami.2026.3654426

Vancouver

Zhou J, Liu C, Jiang Q, Fu X, Hou J, Li X. Semantic Contrast for Domain-Robust Underwater Image Quality Assessment. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(6):6279-6296. doi:10.1109/tpami.2026.3654426

BibTeX
@article{Zhou2026,
  author = {Zhou, Jingchun and Liu, Chunjiang and Jiang, Qiuping and Fu, Xianping and Hou, Junhui and Li, Xuelong},
  title = {Semantic Contrast for Domain-Robust Underwater Image Quality Assessment},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {6},
  pages = {6279--6296},
  doi = {10.1109/tpami.2026.3654426}
}
Kostenlos starten →