Label What Matters: Modality-Balanced and Difficulty-Aware Multimodal Active Learning

• URL: http://arxiv.org/abs/2603.25107v1
• Date: Thu, 26 Mar 2026 07:26:48 GMT
• Title: Label What Matters: Modality-Balanced and Difficulty-Aware Multimodal Active Learning
• Abstract summary: We propose RL-MBA, a reinforcement-learning framework for modality-balanced, difficulty-aware active learning.<n>Experiments on Food101, KineticsSound, and VGGSound demonstrate that RL-MBA consistently outperforms strong baselines.
• Score: 13.136629024689432
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Multimodal learning integrates complementary information from different modalities such as image, text, and audio to improve model performance, but its success relies on large-scale labeled data, which is costly to obtain. Active learning (AL) mitigates this challenge by selectively annotating informative samples. In multimodal settings, many approaches implicitly assume that modality importance is stable across rounds and keep selection rules fixed at the fusion stage, which leaves them insensitive to the dynamic nature of multimodal learning, where the relative value of modalities and the difficulty of instances shift as training proceeds. To address this issue, we propose RL-MBA, a reinforcement-learning framework for modality-balanced, difficulty-aware multimodal active learning. RL-MBA models sample selection as a Markov Decision Process, where the policy adapts to modality contributions, uncertainty, and diversity, and the reward encourages accuracy gains and balance. Two key components drive this adaptability: (1) Adaptive Modality Contribution Balancing (AMCB), which dynamically adjusts modality weights via reinforcement feedback, and (2) Evidential Fusion for DifficultyAware Policy Adjustment (EFDA), which estimates sample difficulty via uncertainty-based evidential fusion to prioritize informative samples. Experiments on Food101, KineticsSound, and VGGSound demonstrate that RL-MBA consistently outperforms strong baselines, improving both classification accuracy and modality fairness under limited labeling budgets.

Related papers

• Model-Agnostic Meta Learning for Class Imbalance Adaptation [3.2488051786523813]
  Class imbalance is a widespread challenge in NLP tasks, hindering robust performance across diverse domains and applications.<n>We introduce Hardness-Aware Meta-Resample (HAMR), a unified framework that adaptively addresses both class imbalance and data difficulty.
  arXiv  Detail & Related papers  (2026-04-20T19:07:56Z)
• Dual-level Modality Debiasing Learning for Unsupervised Visible-Infrared Person Re-Identification [59.59359638389348]
  We propose a Dual-level Modality Debiasing Learning framework that implements debiasing at both the model and optimization levels.<n>Experiments on benchmark datasets demonstrate that DMDL could enable modality-invariant feature learning and a more generalized model.
  arXiv  Detail & Related papers  (2025-12-03T12:43:16Z)
• Improving Multimodal Sentiment Analysis via Modality Optimization and Dynamic Primary Modality Selection [54.10252086842123]
  Multimodal Sentiment Analysis (MSA) aims to predict sentiment from language, acoustic, and visual data in videos.<n>This paper proposes a modality optimization and dynamic primary modality selection framework (MODS)<n>Experiments on four benchmark datasets demonstrate that MODS outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-11-09T11:13:32Z)
• MIDAS: Misalignment-based Data Augmentation Strategy for Imbalanced Multimodal Learning [14.06705718861471]
  Multimodal models often over-rely on dominant modalities, failing to achieve optimal performance.<n>We propose MIDAS, a novel data augmentation strategy that generates misaligned samples with semantically inconsistent cross-modal information.<n>Experiments on multiple multimodal classification benchmarks demonstrate that MIDAS significantly outperforms related baselines in addressing modality imbalance.
  arXiv  Detail & Related papers  (2025-09-30T06:13:17Z)
• MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings [75.0617088717528]
  MoCa is a framework for transforming pre-trained VLM backbones into effective bidirectional embedding models.<n>MoCa consistently improves performance across MMEB and ViDoRe-v2 benchmarks, achieving new state-of-the-art results.
  arXiv  Detail & Related papers  (2025-06-29T06:41:00Z)
• Modality Equilibrium Matters: Minor-Modality-Aware Adaptive Alternating for Cross-Modal Memory Enhancement [13.424541949553964]
  We propose a Shapley-guided alternating training framework that adaptively prioritizes minor modalities to balance and thus enhance the fusion.<n>We evaluate the performance in both balance and accuracy across four multimodal benchmark datasets, where our method achieves state-of-the-art (SOTA) results.
  arXiv  Detail & Related papers  (2025-05-26T02:02:57Z)
• DynCIM: Dynamic Curriculum for Imbalanced Multimodal Learning [27.20479303843989]
  DynCIM is a novel dynamic curriculum learning framework designed to quantify the inherent imbalances from both sample and modality perspectives.<n>DynCIM employs a sample-level curriculum to dynamically assess each sample's difficulty according to prediction deviation, consistency, and stability.<n>A modality-level curriculum measures modality contributions from global and local.
  arXiv  Detail & Related papers  (2025-03-09T05:30:15Z)
• LLMs Can Evolve Continually on Modality for X-Modal Reasoning [62.2874638875554]
  Existing methods rely heavily on modal-specific pretraining and joint-modal tuning, leading to significant computational burdens when expanding to new modalities. We propose PathWeave, a flexible and scalable framework with modal-Path sWitching and ExpAnsion abilities. PathWeave performs comparably to state-of-the-art MLLMs while concurrently reducing parameter training burdens by 98.73%.
  arXiv  Detail & Related papers  (2024-10-26T13:19:57Z)
• On-the-fly Modulation for Balanced Multimodal Learning [53.616094855778954]
  Multimodal learning is expected to boost model performance by integrating information from different modalities. The widely-used joint training strategy leads to imbalanced and under-optimized uni-modal representations. We propose On-the-fly Prediction Modulation (OPM) and On-the-fly Gradient Modulation (OGM) strategies to modulate the optimization of each modality.
  arXiv  Detail & Related papers  (2024-10-15T13:15:50Z)
• Multimodal Imbalance-Aware Gradient Modulation for Weakly-supervised Audio-Visual Video Parsing [107.031903351176]
  Weakly-separated audio-visual video parsing (WS-AVVP) aims to localize the temporal extents of audio, visual and audio-visual event instances. WS-AVVP aims to identify the corresponding event categories with only video-level category labels for training.
  arXiv  Detail & Related papers  (2023-07-05T05:55:10Z)

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.