EUVIMEDEUVIMED entdecken
Crossref

Bridging the Thermal Gap: Data-Model Collaborative Transfer for Infrared Perception

Zhu Liu, Qilong Zhao, Zhirui Fang, Benzhuang Zhang, Jinyuan Liu, Risheng Liu

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026 · 1-17

DOI: 10.1109/tpami.2026.3754462 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026. Verfasst von Zhu Liu und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Infrared visual perception fundamentally differs from visible-domain vision due to its distinct thermal imaging mechanism and varying imaging conditions. Existing methods typically decouple data construction from model transfer, overlooking their interdependence: model accuracy and robustness depend critically on the coverage and composition of training observations, while effective model transfer requires explicit modeling of infrared-specific imaging characteristics. To address this issue, we propose a data-model collaborative transfer framework for infrared visual perception. At the data level, a task-responsive generator learns weights over a feasible infrared imaging-variation space to construct informative training observations. At the model level, a formation-guided representation module derives complementary radiance-structure and response-detail descriptors from infrared observations. We further design a thermal-aware adapter that uses these descriptors to modulate intermediate representations and produce lightweight residual corrections for model transfer. A single-loop training strategy coordinates data generation, representation learning, and adapter optimization without expensive nested optimization. Extensive experiments on image enhancement, depth estimation, small-target detection, and semantic segmentation demonstrate consistent performance improvements across multiple foundation-model backbones with a small trainable parameter budget.

Zitieren

APA

Liu, Z., Zhao, Q., Fang, Z., Zhang, B., Liu, J., & Liu, R. (2026). Bridging the Thermal Gap: Data-Model Collaborative Transfer for Infrared Perception. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1-17. https://doi.org/10.1109/tpami.2026.3754462

Vancouver

Liu Z, Zhao Q, Fang Z, Zhang B, Liu J, Liu R. Bridging the Thermal Gap: Data-Model Collaborative Transfer for Infrared Perception. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026:1-17. doi:10.1109/tpami.2026.3754462

BibTeX
@article{Liu2026,
  author = {Liu, Zhu and Zhao, Qilong and Fang, Zhirui and Zhang, Benzhuang and Liu, Jinyuan and Liu, Risheng},
  title = {Bridging the Thermal Gap: Data-Model Collaborative Transfer for Infrared Perception},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  pages = {1--17},
  doi = {10.1109/tpami.2026.3754462}
}
Kostenlos starten →