Wang, Qingwang, Ouyang, Junlin, Shen, Tao, Gu, Yanfeng, Ullah, Sami, Al-Antary, Mohammad, Alasmary, Hisham, Waqas, Muhammad ORCID: https://orcid.org/0000-0003-0814-7544, Tang, Bo-Hui and Halim, Zahid (2026) Complementary information mining for redundancy and weakly aligned RGB-T semantic segmentation. IEEE Transactions on Geoscience and Remote Sensing, 64:5901414. pp. 1-14. ISSN 0196-2892 (Print), 1558-0644 (Online) (doi:10.1109/TGRS.2026.3654044)

Preview

PDF (Accepted Manuscript) 52355 WAQAS_Complementary_Information_Mining_For_Redundancy_And_Weakly_Aligned_RGB-T_(AAM)_2026.pdf - Accepted Version Download (49MB) | Preview

Abstract

Multimodal data can effectively improve the accuracy and robustness of traditional RGB image semantic segmentation. However, the redundant information between cross-modal data hinders the complementary information mining of each modality. And the data misalignment between modes will aggravate the above effects. In this article, we propose a complementary information mining network (CIMNet) for RGB-thermal (RGB-T) semantic segmentation. We comprehensively consider the link between the difficulty of redundant information mining and modality misalignment. Through mutual information minimization and adaptive update of modality bias, we achieve more accurate and robust segmentation performance in complex environments. Specifically, we introduce a complementary information promotion and amplification (CIPA) module via mutual information minimization and channel attention mechanism to prevent a multimodality network from focusing on redundant information and amplify the informative cross-modality features. Then, we design a spatial-channel sequential feature rectification (SCSFR) module with adaptive offset modeling to calibrate the modality misalignment features. Extensive experiments on public datasets demonstrate that our CIMNet outperforms other state-of-the-art (SOTA) methods in terms of objective metrics and subjective visual comparisons. The code will be accessible at https://github.com/KustTeamWQW/CIMNet.

Item Type:	Article
Additional Information:	© IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, including reprinting, republishing, advertising, promotional purposes, creating new collective works, resale, or redistribution. The published version is available a thttps://doi.org/10.1109/TGRS.2026.3654044.
Uncontrolled Keywords:	semantic segmentation, feature extraction, mutual information, thermal sensors, semantics, lighting, accuracy, transformers, minimization, data mining, cross-modality, feature rectification, mutual information, minimization, RGB-thermal (RGB-T) semantic segmentation, feature extraction
Subjects:	Q Science > Q Science (General) Q Science > QA Mathematics Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Faculty / School / Research Centre / Research Group:	Faculty of Engineering & Science Faculty of Engineering & Science > School of Computing & Mathematical Sciences (CMS)
Last Modified:	29 Jan 2026 14:30
URI:	https://gala.gre.ac.uk/id/eprint/52355

Actions (login required)

View Item

Downloads