paper-with-me

Papers

Classifier-guided Gradient Modulation for Enhanced Multimodal Learning

2024-11-03 · Zirun Guo, Tao Jin, Jingyuan Chen, Zhou Zhao

Multimodal learning has developed very fast in recent years. However, during the multimodal training process, the model tends to rely on only one modality based on which it could learn faster, thus leading to inadequate use of other modalities. Existing methods to balance the training process always have some limitations on the loss functions, optimizers and the number of modalities and only consider modulating the magnitude of the gradients while ignoring the directions of the gradients. To solve these problems, in this paper, we present a novel method to balance multimodal learning with Classifier-Guided Gradient Modulation (CGGM), considering both the magnitude and directions of the gradients. We conduct extensive experiments on four multimodal datasets: UPMC-Food 101, CMU-MOSI, IEMOCAP and BraTS 2021, covering classification, regression and segmentation tasks. The results show that CGGM outperforms all the baselines and other state-of-the-art methods consistently, demonstrating its effectiveness and versatility. Our code is available at https://github.com/zrguo/CGGM.

📄 PDF Abstract BibTeX arXiv:2411.01409

Code (1)

zrguo/cggm 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Layer-Specific Lipschitz Modulation for Fault-Tolerant Multimodal Representation Learning

2026-03-26 · Diyar Altinses, Andreas Schwung arxiv

Modern multimodal systems deployed in industrial and safety-critical environments must remain reliable under partial sensor failures, signal degradation, or cross-modal inconsistencies. This work introduces a mathematica…

Self-Supervised Anomaly DetectionRepresentation Learning

Balanced Multimodal Learning via On-the-fly Gradient Modulation

2022-03-29 · CVPR 2022 1 · Xiaokang Peng, Yake Wei, Andong Deng, Dong Wang 외

Multimodal learning helps to comprehensively understand the world, by integrating different senses. Accordingly, multiple input modalities are expected to boost model performance, but we actually find that they are not f…

PaSE: Prototype-aligned Calibration and Shapley-based Equilibrium for Multimodal Sentiment Analysis

2025-11-16 · Kang He, Boyu Chen, Yuzhe Ding, Fei Li 외 arxiv

Multimodal Sentiment Analysis (MSA) seeks to understand human emotions by integrating textual, acoustic, and visual signals. Although multimodal fusion is designed to leverage cross-modal complementarity, real-world scen…

Multimodal Sentiment Analysis

SLGNet: Synergizing Structural Priors and Language-Guided Modulation for Multimodal Object Detection

2026-01-05 · Xiantai Xiang, Guangyao Zhou, Zixiao Wen, Wenshuai Li 외 arxiv

Multimodal object detection leveraging RGB and Infrared (IR) images is pivotal for robust perception in all-weather scenarios. While recent adapter-based approaches efficiently transfer RGB-pretrained foundation models t…

Object Detection

More than Vanilla Fusion: a Simple, Decoupling-free, Attention Module for Multimodal Fusion Based on Signal Theory

2023-12-12 · Peiwen Sun, Yifan Zhang, Zishan Liu, Donghao Chen 외

The vanilla fusion methods still dominate a large percentage of mainstream audio-visual tasks. However, the effectiveness of vanilla fusion from a theoretical perspective is still worth discussing. Thus, this paper recon…