MER-DG: Modality-Entropy Regularization for Multimodal Domain Generalization

• URL: http://arxiv.org/abs/2605.01967v1
• Date: Sun, 03 May 2026 16:53:26 GMT
• Title: MER-DG: Modality-Entropy Regularization for Multimodal Domain Generalization
• Abstract summary: We propose Modality-Entropy Regularization for Domain Generalization (MER-DG)<n>MER-DG maximizes the entropy of each encoder's feature distribution to preserve feature diversity.<n>Experiments on EPIC-Kitchens and HAC benchmarks demonstrate average improvements of approximately 5% over standard fusion.
• Score: 6.929741688224915
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deploying multimodal models in real-world scenarios requires generalization to new environments where recording conditions differ from training, a challenge known as multimodal domain generalization (MMDG). Standard architectures employ separate encoders for each modality and a fusion module, training the system end-to-end by optimizing on the fused features. In this paper, we identify that such joint optimization causes encoders to exploit cross-modal co-occurrences, statistical relationships between modalities that arise from source-specific recording conditions, rather than learning domain-invariant features. We term this failure mode Fusion Overfitting. To address this, we propose Modality-Entropy Regularization for Domain Generalization (MER-DG), which maximizes the entropy of each encoder's feature distribution to preserve feature diversity. MER-DG is architecture-agnostic and integrates into existing multimodal frameworks as an additive loss term. Extensive experiments on EPIC-Kitchens and HAC benchmarks demonstrate average improvements of approximately 5% over standard fusion and approximately 2% over state-of-the-art methods.

Related papers

• MMDG-Bench: A Benchmark for Multimodal Domain Generalization [53.423523300548766]
  Multi-modal Domain Generalization seeks to leverage complementary modalities to enhance model robustness on unseen domains.<n>Current MMDG research is largely confined to action recognition and lacks standardized evaluation protocols.<n>We introduce MMDG-Bench, a comprehensive benchmark featuring two foundational frameworks: DG then MML (D2M) and MML then DG (M2D)
  arXiv  Detail & Related papers  (2026-05-30T20:52:49Z)
• Multi-modal cross-domain mixed fusion model with dual disentanglement for fault diagnosis under unseen working conditions [7.135832969368086]
  This paper proposes a multi-modal cross-domain mixed fusion model with dual disentanglement for fault diagnosis.<n>Experiments are conducted on induction motor fault diagnosis under both unseen constant and time-varying working conditions.
  arXiv  Detail & Related papers  (2025-12-31T07:10:32Z)
• Modality-Collaborative Low-Rank Decomposers for Few-Shot Video Domain Adaptation [74.16390314862801]
  We study the challenging task of Few-Shot Video Domain Adaptation (FSVDA)<n>We introduce a novel framework of Modality-Collaborative LowRank Decomposers (MC-LRD) to decompose modality-unique and modality-shared features.<n>Our model achieves significant improvements over existing methods.
  arXiv  Detail & Related papers  (2025-11-24T03:09:59Z)
• FindRec: Stein-Guided Entropic Flow for Multi-Modal Sequential Recommendation [57.577843653775]
  We propose textbfFindRec (textbfFlexible unified textbfinformation textbfdisentanglement for multi-modal sequential textbfRecommendation)<n>A Stein kernel-based Integrated Information Coordination Module (IICM) theoretically guarantees distribution consistency between multimodal features and ID streams.<n>A cross-modal expert routing mechanism that adaptively filters and combines multimodal features based on their contextual relevance.
  arXiv  Detail & Related papers  (2025-07-07T04:09:45Z)
• Bridging Domain Generalization to Multimodal Domain Generalization via Unified Representations [43.07575348801021]
  Domain Generalization (DG) aims to enhance model robustness in unseen or distributionally shifted target domains through training exclusively on source domains.<n>A key challenge in Multi-modal Domain Generalization (MMDG) has emerged: enabling models trained on multi-modal sources to generalize to unseen target distributions within the same modality set.<n>We propose a novel approach that leverages Unified Representations to map different paired modalities together.
  arXiv  Detail & Related papers  (2025-07-04T05:17:32Z)
• Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models [54.196385799229006]
  This survey provides the first comprehensive review of advances from traditional approaches to foundation models.<n>It covers: (1) Multimodal domain adaptation; (2) Multimodal test-time adaptation; (3) Multimodal domain generalization; (4) Domain adaptation and generalization with the help of multimodal foundation models; and (5) Adaptation of multimodal foundation models.
  arXiv  Detail & Related papers  (2025-01-30T18:59:36Z)
• SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalization [13.456240733175767]
  SimMMDG is a framework to overcome the challenges of achieving domain generalization in multi-modal scenarios. We employ supervised contrastive learning on the modality-shared features to ensure they possess joint properties and impose distance constraints. Our framework is theoretically well-supported and achieves strong performance in multi-modal DG on the EPIC-Kitchens dataset and the novel Human-Animal-Cartoon dataset.
  arXiv  Detail & Related papers  (2023-10-30T17:58:09Z)
• Exploiting modality-invariant feature for robust multimodal emotion recognition with missing modalities [76.08541852988536]
  We propose to use invariant features for a missing modality imagination network (IF-MMIN) We show that the proposed model outperforms all baselines and invariantly improves the overall emotion recognition performance under uncertain missing-modality conditions.
  arXiv  Detail & Related papers  (2022-10-27T12:16:25Z)
• A Novel Unified Conditional Score-based Generative Framework for Multi-modal Medical Image Completion [54.512440195060584]
  We propose the Unified Multi-Modal Conditional Score-based Generative Model (UMM-CSGM) to take advantage of Score-based Generative Model (SGM) UMM-CSGM employs a novel multi-in multi-out Conditional Score Network (mm-CSN) to learn a comprehensive set of cross-modal conditional distributions. Experiments on BraTS19 dataset show that the UMM-CSGM can more reliably synthesize the heterogeneous enhancement and irregular area in tumor-induced lesions.
  arXiv  Detail & Related papers  (2022-07-07T16:57:21Z)
• Compound Domain Generalization via Meta-Knowledge Encoding [55.22920476224671]
  We introduce Style-induced Domain-specific Normalization (SDNorm) to re-normalize the multi-modal underlying distributions. We harness the prototype representations, the centroids of classes, to perform relational modeling in the embedding space. Experiments on four standard Domain Generalization benchmarks reveal that COMEN exceeds the state-of-the-art performance without the need of domain supervision.
  arXiv  Detail & Related papers  (2022-03-24T11:54:59Z)
• Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions [91.63716984911278]
  We introduce a novel Mixture of Normal-Inverse Gamma distributions (MoNIG) algorithm, which efficiently estimates uncertainty in principle for adaptive integration of different modalities and produces a trustworthy regression result. Experimental results on both synthetic and different real-world data demonstrate the effectiveness and trustworthiness of our method on various multimodal regression tasks.
  arXiv  Detail & Related papers  (2021-11-11T14:28:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.