paper-with-me

Papers

DynCIM: Dynamic Curriculum for Imbalanced Multimodal Learning

2025-03-09 · Chengxuan Qian, Kai Han, JingChao Wang, Zhenlong Yuan, Rui Qian, Chongwen Lyu, Jun Chen, Zhe Liu

Multimodal learning integrates complementary information from diverse modalities to enhance the decision-making process. However, the potential of multimodal collaboration remains under-exploited due to disparities in data quality and modality representation capabilities. To address this, we introduce DynCIM, a novel dynamic curriculum learning framework designed to quantify the inherent imbalances from both sample and modality perspectives. DynCIM employs a sample-level curriculum to dynamically assess each sample's difficulty according to prediction deviation, consistency, and stability, while a modality-level curriculum measures modality contributions from global and local. Furthermore, a gating-based dynamic fusion mechanism is introduced to adaptively adjust modality contributions, minimizing redundancy and optimizing fusion effectiveness. Extensive experiments on six multimodal benchmarking datasets, spanning both bimodal and trimodal scenarios, demonstrate that DynCIM consistently outperforms state-of-the-art methods. Our approach effectively mitigates modality and sample imbalances while enhancing adaptability and robustness in multimodal learning tasks. Our code is available at https://github.com/Raymond-Qiancx/DynCIM.

📄 PDF Abstract BibTeX arXiv:2503.06456

Code (1)

raymond-qiancx/dyncim 공식 구현

Tasks

BenchmarkingDecision Making

Similar Papers 제목 키워드 기반

CLIMD: A Curriculum Learning Framework for Imbalanced Multimodal Diagnosis

2025-08-03 · Kai Han, Chongwen Lyu, Lele Ma, Chengxuan Qian 외 arxiv

Clinicians usually combine information from multiple sources to achieve the most accurate diagnosis, and this has sparked increasing interest in leveraging multimodal deep learning for diagnosis. However, in real clinica…

Multimodal Deep Learning

Improving Imbalanced Text Classification with Dynamic Curriculum Learning

2022-10-25 · xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao

Recent advances in pre-trained language models have improved the performance for text classification tasks. However, little attention is paid to the priority scheduling strategy on the samples during training. Humans acq…

ClassificationSchedulingtext-classificationText Classification

Dynamic Curriculum Learning for Imbalanced Data Classification

2019-01-21 · ICCV 2019 10 · Yiru Wang, Weihao Gan, Jie Yang, Wei Wu 외

Human attribute analysis is a challenging task in the field of computer vision, since the data is largely imbalance-distributed. Common techniques such as re-sampling and cost-sensitive learning require prior-knowledge t…

AttributeClassificationGeneral ClassificationMetric Learning

Leveraging Self-Paced Curriculum Learning for Enhanced Modality Balance in Multimodal Conversational Emotion Recognition

2026-05-20 · Phuong-Anh Nguyen, The-Son Le, Duc-Trong Le, Cam-Van Thi Nguyen arxiv

Multimodal Emotion Recognition in Conversations (MERC) is a crucial task for understanding human interactions, where multimodal approaches integrating language, facial expressions, and vocal tone have achieved significan…

Multimodal Emotion Recognition

Overcoming Uncertain Incompleteness for Robust Multimodal Sequential Diagnosis Prediction via Curriculum Data Erasing Guided Knowledge Distillation

2024-07-28 · Heejoon Koo

In this paper, we present NECHO v2, a novel framework designed to enhance the predictive accuracy of multimodal sequential patient diagnoses under uncertain missing visit sequences, a common challenge in real clinical se…

Knowledge DistillationSequential Diagnosis