M-SpecGene: Generalized Foundation Model for RGBT Multispectral Vision

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhou, Kailai, Yang, Fuqiang, Wang, Shixian, Wen, Bihan, Zi, Chongde, Chen, Linsen, Shen, Qiu, Cao, Xun
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915412933869568
author Zhou, Kailai
Yang, Fuqiang
Wang, Shixian
Wen, Bihan
Zi, Chongde
Chen, Linsen
Shen, Qiu
Cao, Xun
author_facet Zhou, Kailai
Yang, Fuqiang
Wang, Shixian
Wen, Bihan
Zi, Chongde
Chen, Linsen
Shen, Qiu
Cao, Xun
contents RGB-Thermal (RGBT) multispectral vision is essential for robust perception in complex environments. Most RGBT tasks follow a case-by-case research paradigm, relying on manually customized models to learn task-oriented representations. Nevertheless, this paradigm is inherently constrained by artificial inductive bias, modality bias, and data bottleneck. To address these limitations, we make the initial attempt to build a Generalized RGBT MultiSpectral foundation model (M-SpecGene), which aims to learn modality-invariant representations from large-scale broad data in a self-supervised manner. M-SpecGene provides new insights into multispectral fusion and integrates prior case-by-case studies into a unified paradigm. Considering the unique characteristic of information imbalance in RGBT data, we introduce the Cross-Modality Structural Sparsity (CMSS) metric to quantify the information density across two modalities. Then we develop the GMM-CMSS progressive masking strategy to facilitate a flexible, easy-to-hard, and object-centric pre-training process. Comprehensive experiments validate M-SpecGene's generalizability across eleven datasets for four RGBT downstream tasks. The code will be available at https://github.com/CalayZhou/M-SpecGene.
format Preprint
id arxiv_https___arxiv_org_abs_2507_16318
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle M-SpecGene: Generalized Foundation Model for RGBT Multispectral Vision
Zhou, Kailai
Yang, Fuqiang
Wang, Shixian
Wen, Bihan
Zi, Chongde
Chen, Linsen
Shen, Qiu
Cao, Xun
Computer Vision and Pattern Recognition
RGB-Thermal (RGBT) multispectral vision is essential for robust perception in complex environments. Most RGBT tasks follow a case-by-case research paradigm, relying on manually customized models to learn task-oriented representations. Nevertheless, this paradigm is inherently constrained by artificial inductive bias, modality bias, and data bottleneck. To address these limitations, we make the initial attempt to build a Generalized RGBT MultiSpectral foundation model (M-SpecGene), which aims to learn modality-invariant representations from large-scale broad data in a self-supervised manner. M-SpecGene provides new insights into multispectral fusion and integrates prior case-by-case studies into a unified paradigm. Considering the unique characteristic of information imbalance in RGBT data, we introduce the Cross-Modality Structural Sparsity (CMSS) metric to quantify the information density across two modalities. Then we develop the GMM-CMSS progressive masking strategy to facilitate a flexible, easy-to-hard, and object-centric pre-training process. Comprehensive experiments validate M-SpecGene's generalizability across eleven datasets for four RGBT downstream tasks. The code will be available at https://github.com/CalayZhou/M-SpecGene.
title M-SpecGene: Generalized Foundation Model for RGBT Multispectral Vision
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.16318