Salvato in:
Dettagli Bibliografici
Autori principali: Mao, Fangyuan, Wang, Shuo, Mei, Jilin, Lu, Shun, Min, Chen, Liu, Fuyang, Feng, Xiaokun, Wu, Meiqi, Hu, Yu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.15642
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910214975913984
author Mao, Fangyuan
Wang, Shuo
Mei, Jilin
Lu, Shun
Min, Chen
Liu, Fuyang
Feng, Xiaokun
Wu, Meiqi
Hu, Yu
author_facet Mao, Fangyuan
Wang, Shuo
Mei, Jilin
Lu, Shun
Min, Chen
Liu, Fuyang
Feng, Xiaokun
Wu, Meiqi
Hu, Yu
contents Joint RGB-infrared perception is essential for achieving robustness under diverse weather and illumination conditions. Although foundation models excel within single modalities, they suffer from substantial cross-modal degradation, an issue we attribute to a pattern shortcut, i.e., a modal bias that prioritizes superficial sensor patterns over underlying semantics. To address this problem, we introduce UNIV, a Unified foundation model for Infrared and Visible modalities. At the core of UNIV lies Patch Cross-modal Contrastive Learning (PCCL), a self-supervised contrastive learning strategy that constructs a unified cross-modal feature space. PCCL employs a frozen pre-trained model to sample pseudo patch pairs based on semantic similarity, and aligns infrared-visible representations by attracting semantically related pairs while repelling unrelated ones. This process simultaneously enhances cross-modal alignment and inter-class semantic separability, guiding the model to focus on semantic structure rather than falling into pattern shortcuts. To further enable cross-modal learning, we introduce MVIP, the most comprehensive visible-infrared benchmark to date, containing 98,992 precisely aligned image pairs across diverse scenes. Extensive experiments demonstrate UNIV's superior performance on infrared tasks (+1.7 mIoU for semantic segmentation and +0.7 mAP for detection), while maintaining competitive accuracy on RGB tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2509_15642
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UNIV: Unified Foundation Model for Infrared and Visible Modalities
Mao, Fangyuan
Wang, Shuo
Mei, Jilin
Lu, Shun
Min, Chen
Liu, Fuyang
Feng, Xiaokun
Wu, Meiqi
Hu, Yu
Computer Vision and Pattern Recognition
Joint RGB-infrared perception is essential for achieving robustness under diverse weather and illumination conditions. Although foundation models excel within single modalities, they suffer from substantial cross-modal degradation, an issue we attribute to a pattern shortcut, i.e., a modal bias that prioritizes superficial sensor patterns over underlying semantics. To address this problem, we introduce UNIV, a Unified foundation model for Infrared and Visible modalities. At the core of UNIV lies Patch Cross-modal Contrastive Learning (PCCL), a self-supervised contrastive learning strategy that constructs a unified cross-modal feature space. PCCL employs a frozen pre-trained model to sample pseudo patch pairs based on semantic similarity, and aligns infrared-visible representations by attracting semantically related pairs while repelling unrelated ones. This process simultaneously enhances cross-modal alignment and inter-class semantic separability, guiding the model to focus on semantic structure rather than falling into pattern shortcuts. To further enable cross-modal learning, we introduce MVIP, the most comprehensive visible-infrared benchmark to date, containing 98,992 precisely aligned image pairs across diverse scenes. Extensive experiments demonstrate UNIV's superior performance on infrared tasks (+1.7 mIoU for semantic segmentation and +0.7 mAP for detection), while maintaining competitive accuracy on RGB tasks.
title UNIV: Unified Foundation Model for Infrared and Visible Modalities
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.15642