paper-with-me

홈 › Papers

Gradient-Guided Modality Decoupling for Missing-Modality Robustness

2024-02-26 · Hao Wang, Shengda Luo, Guosheng Hu, JianGuo Zhang

Multimodal learning with incomplete input data (missing modality) is practical and challenging. In this work, we conduct an in-depth analysis of this challenge and find that modality dominance has a significant negative impact on the model training, greatly degrading the missing modality performance. Motivated by Grad-CAM, we introduce a novel indicator, gradients, to monitor and reduce modality dominance which widely exists in the missing-modality scenario. In aid of this indicator, we present a novel Gradient-guided Modality Decoupling (GMD) method to decouple the dependency on dominating modalities. Specifically, GMD removes the conflicted gradient components from different modalities to achieve this decoupling, significantly improving the performance. In addition, to flexibly handle modal-incomplete data, we design a parameter-efficient Dynamic Sharing (DS) framework which can adaptively switch on/off the network parameters based on whether one modality is available. We conduct extensive experiments on three popular multimodal benchmarks, including BraTS 2018 for medical segmentation, CMU-MOSI, and CMU-MOSEI for sentiment analysis. The results show that our method can significantly outperform the competitors, showing the effectiveness of the proposed solutions. Our code is released here: https://github.com/HaoWang420/Gradient-guided-Modality-Decoupling.

📄 PDF Abstract BibTeX arXiv:2402.16318

Code (1)

haowang420/gradient-guided-modality-decoupling 공식 구현 pytorch

Tasks

Sentiment Analysis

Similar Papers 제목 키워드 기반

RTFDNet: Fusion-Decoupling for Robust RGB-T Segmentation

2026-03-10 · Kunyu Tan, Mingjian Liang arxiv

RGB-Thermal (RGB-T) semantic segmentation is essential for robotic systems operating in low-light or dark environments. However, traditional approaches often overemphasize modality balance, resulting in limited robustnes…

Knowledge DistillationSemantic Segmentation

Compass: Degradation-Simulated Reciprocal Learning with Lightweight Needle RWKV for Multimodal Crack Segmentation under Missing Modalities

2026-08-04 · Hui Liu, Chen Jia, Fan Shi, Xu Cheng 외 arxiv

In multimodal crack segmentation for industrial facilities, the key challenge is preventing missing modalities from degrading pixel-level performance while maintaining low computational cost. Existing methods struggle to…

Crack Segmentation

Buffer replay enhances the robustness of multimodal learning under missing-modality

2025-11-28 · Hongye Zhu, Xuan Liu, Yanwen Ba, Jingye Xue 외 arxiv

Missing modalities consistently lead to significant performance degradation in multimodal models. Existing approaches either synthesize missing modalities at high computational cost or apply prompt-based fine-tuning that…

Diverse Semantics-Guided Feature Alignment and Decoupling for Visible-Infrared Person Re-Identification

2025-05-01 · Neng Dong, Shuanglin Yan, Liyan Zhang, Jinhui Tang

Visible-Infrared Person Re-Identification (VI-ReID) is a challenging task due to the large modality discrepancy between visible and infrared images, which complicates the alignment of their features into a suitable commo…

Person Re-Identification

Enhance-then-Balance Modality Collaboration for Robust Multimodal Sentiment Analysis

2026-04-14 · Kang He, Yuzhe Ding, Xinrong Wang, Fei Li 외 arxiv

Multimodal sentiment analysis (MSA) integrates heterogeneous text, audio, and visual signals to infer human emotions. While recent approaches leverage cross-modal complementarity, they often struggle to fully utilize wea…

Multimodal Sentiment Analysis