Beyond Modality Fusion: Deep Ensembles for Multimodal Classification

• URL: http://arxiv.org/abs/2607.05019v2
• Date: Tue, 07 Jul 2026 07:13:34 GMT
• Title: Beyond Modality Fusion: Deep Ensembles for Multimodal Classification
• Abstract summary: In multimodal classification, late-fusion approaches classifyd modality-specific features extracted by unimodal neural networks.<n>We show that multimodal data can be effectively classified without any explicit modality fusion, using deep ensembles of unimodal networks.<n>We propose a synthetic multimodal framework that allows control over both the number of modalities and their predictive strength.
• Score: 0.38059763597999
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In multimodal classification, late-fusion approaches classify concatenated modality-specific features extracted by unimodal neural networks. When modality imbalance is pronounced, various regularization techniques have been proposed to balance the learning process and overcome the inferior performance of late-fusion networks. In contrast, this work demonstrates that multimodal data can be effectively classified without any explicit modality fusion, using deep ensembles of unimodal networks. We systematically compare deep ensembles to late-fusion networks at equal parameter count and show that ensembles consistently outperform state-of-the-art late-fusion methods designed to address modality imbalance. This advantage also holds over intermediate-fusion techniques we evaluated and over hybrid methods that combine unimodal and multimodal predictions. We propose and empirically validate a method for selecting the number of models per modality in an ensemble, avoiding computationally expensive exhaustive search. Under extreme modality imbalance and small ensemble sizes, the heuristic indicates that ensembles of unimodal models trained solely on the stronger modality are preferable; as the ensemble scales up, incorporating models from the weaker modality becomes beneficial. Both predictions align with our empirical findings. To systematically explore the challenges of optimizing multimodal models, we propose a synthetic multimodal framework that allows control over both the number of modalities and their predictive strength; our findings are consistent across synthetic and real-world datasets. Finally, by fitting scaling laws to bimodal datasets, we estimate the asymptotic performance of ensembles.

Related papers

• DAIF: A Data-Driven Intermediate Fusion Framework for Multimodal Supervised Learning via Approximate Message Passing [11.222071637855079]
  DAIF is a data adaptive intermediate fusion framework to learn fusion structure directly from data.<n>We operate under a Bayesian multimodal factor model where the prior on the latent factors determines the cross-modal dependence.<n>Our method clusters modalities based on estimated intermodal dependence, then performs clusterwise empirical Bayes estimation of the priors.
  arXiv  Detail & Related papers  (2026-08-03T18:10:58Z)
• Omnimodal Dataset Distillation via High-order Proxy Alignment [59.74134776126595]
  We propose HoPA, a unified method that captures high-order cross-modal alignments via a proxy structure.<n>Our method avoids the complexity of pairwise modality modeling and enables scalable proxy analysis across heterogeneous modalities.
  arXiv  Detail & Related papers  (2026-04-12T14:47:41Z)
• AlignMamba-2: Enhancing Multimodal Fusion and Sentiment Analysis with Modality-Aware Mamba [56.52470564147458]
  We propose textbfAlignMamba-2, an effective and efficient framework for multimodal fusion and sentiment analysis.<n>Our approach introduces a dual alignment strategy that regularizes the model using both Optimal Transport distance and Maximum Mean Discrepancy.<n>More importantly, we design a Modality-Aware Mamba layer, which employs a Mixture-of-Experts architecture with modality-specific and modality-shared experts.
  arXiv  Detail & Related papers  (2026-03-19T03:47:21Z)
• Calibrated Multimodal Representation Learning with Missing Modalities [100.55774771852468]
  Multimodal representation learning harmonizes distinct modalities by aligning them into a unified latent space.<n>Recent research generalizes traditional cross-modal alignment to produce enhanced multimodal synergy but requires all modalities to be present for a common instance.<n>We provide theoretical insights into this issue from an anchor shift perspective.<n>We propose CalMRL for multimodal representation learning to calibrate incomplete alignments caused by missing modalities.
  arXiv  Detail & Related papers  (2025-11-15T05:01:43Z)
• NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching [64.10695425442164]
  We introduce NExT-OMNI, an open-source omnimodal foundation model that achieves unified modeling through discrete flow paradigms.<n>Trained on large-scale interleaved text, image, video, and audio data, NExT-OMNI delivers competitive performance on multimodal generation and understanding benchmarks.<n>To advance further research, we release training details, data protocols, and open-source both the code and model checkpoints.
  arXiv  Detail & Related papers  (2025-10-15T16:25:18Z)
• Rebalanced Multimodal Learning with Data-aware Unimodal Sampling [39.77348232514481]
  We propose a novel MML approach called underlineData-aware underlineUnimodal underlineSampling(method)<n>Based on the learning status, we propose a reinforcement learning(RL)-based data-aware unimodal sampling approaches.<n>Our method can be seamlessly incorporated into almost all existing multimodal learning approaches as a plugin.
  arXiv  Detail & Related papers  (2025-03-05T08:19:31Z)
• Bridging the inference gap in Mutimodal Variational Autoencoders [6.246098300155483]
  Multimodal Variational Autoencoders offer versatile and scalable methods for generating unobserved modalities from observed ones.<n>Recent models using mixturesof-experts aggregation suffer from theoretically grounded limitations that restrict their generation quality on complex datasets.<n>We propose a novel interpretable model able to learn both joint and conditional distributions without introducing mixture aggregation.
  arXiv  Detail & Related papers  (2025-02-06T10:43:55Z)
• Regularized Neural Ensemblers [55.15643209328513]
  In this study, we explore employing regularized neural networks as ensemble methods.<n>Motivated by the risk of learning low-diversity ensembles, we propose regularizing the ensembling model by randomly dropping base model predictions.<n>We demonstrate this approach provides lower bounds for the diversity within the ensemble, reducing overfitting and improving generalization capabilities.
  arXiv  Detail & Related papers  (2024-10-06T15:25:39Z)
• Dealing with All-stage Missing Modality: Towards A Universal Model with Robust Reconstruction and Personalization [14.606035444283984]
  Current approaches focus on developing models that handle modality-incomplete inputs during inference. We propose a robust universal model with modality reconstruction and model personalization. Our method has been extensively validated on two brain tumor segmentation benchmarks.
  arXiv  Detail & Related papers  (2024-06-04T06:07:24Z)
• Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding [62.70450216120704]
  Unsupervised pre-training has shown great success in skeleton-based action understanding. We propose a Unified Multimodal Unsupervised Representation Learning framework, called UmURL. UmURL exploits an efficient early-fusion strategy to jointly encode the multi-modal features in a single-stream manner.
  arXiv  Detail & Related papers  (2023-11-06T13:56:57Z)
• Sequential Bayesian Neural Subnetwork Ensembles [4.6354120722975125]
  We propose an approach for sequential ensembling of dynamic Bayesian neuralworks that consistently maintains reduced model complexity throughout the training process. Our proposed approach outperforms traditional dense and sparse deterministic and Bayesian ensemble models in terms of prediction accuracy, uncertainty estimation, out-of-distribution detection, and adversarial robustness.
  arXiv  Detail & Related papers  (2022-06-01T22:57:52Z)

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.