Saved in:
Bibliographic Details
Main Authors: Gao, Xiyuan, Cao, Bing, Zhu, Pengfei, Wang, Nannan, Hu, Qinghua
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.01240
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912175463858176
author Gao, Xiyuan
Cao, Bing
Zhu, Pengfei
Wang, Nannan
Hu, Qinghua
author_facet Gao, Xiyuan
Cao, Bing
Zhu, Pengfei
Wang, Nannan
Hu, Qinghua
contents The strength of multimodal learning lies in its ability to integrate information from various sources, providing rich and comprehensive insights. However, in real-world scenarios, multi-modal systems often face the challenge of dynamic modality contributions, the dominance of different modalities may change with the environments, leading to suboptimal performance in multimodal learning. Current methods mainly enhance weak modalities to balance multimodal representation bias, which inevitably optimizes from a partialmodality perspective, easily leading to performance descending for dominant modalities. To address this problem, we propose an Asymmetric Reinforcing method against Multimodal representation bias (ARM). Our ARM dynamically reinforces the weak modalities while maintaining the ability to represent dominant modalities through conditional mutual information. Moreover, we provide an in-depth analysis that optimizing certain modalities could cause information loss and prevent leveraging the full advantages of multimodal data. By exploring the dominance and narrowing the contribution gaps between modalities, we have significantly improved the performance of multimodal learning, making notable progress in mitigating imbalanced multimodal learning.
format Preprint
id arxiv_https___arxiv_org_abs_2501_01240
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Asymmetric Reinforcing against Multi-modal Representation Bias
Gao, Xiyuan
Cao, Bing
Zhu, Pengfei
Wang, Nannan
Hu, Qinghua
Computer Vision and Pattern Recognition
The strength of multimodal learning lies in its ability to integrate information from various sources, providing rich and comprehensive insights. However, in real-world scenarios, multi-modal systems often face the challenge of dynamic modality contributions, the dominance of different modalities may change with the environments, leading to suboptimal performance in multimodal learning. Current methods mainly enhance weak modalities to balance multimodal representation bias, which inevitably optimizes from a partialmodality perspective, easily leading to performance descending for dominant modalities. To address this problem, we propose an Asymmetric Reinforcing method against Multimodal representation bias (ARM). Our ARM dynamically reinforces the weak modalities while maintaining the ability to represent dominant modalities through conditional mutual information. Moreover, we provide an in-depth analysis that optimizing certain modalities could cause information loss and prevent leveraging the full advantages of multimodal data. By exploring the dominance and narrowing the contribution gaps between modalities, we have significantly improved the performance of multimodal learning, making notable progress in mitigating imbalanced multimodal learning.
title Asymmetric Reinforcing against Multi-modal Representation Bias
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.01240