English
Related papers

Related papers: Towards Uniformity and Alignment for Multimodal Re…

200 papers

The world provides us with data of multiple modalities. Intuitively, models fusing data from different modalities outperform their uni-modal counterparts, since more information is aggregated. Recently, joining the success of deep learning,…

Machine Learning · Computer Science 2021-10-27 Yu Huang , Chenzhuang Du , Zihui Xue , Xuanyao Chen , Hang Zhao , Longbo Huang

This paper proposes a method for representation learning of multimodal data using contrastive losses. A traditional approach is to contrast different modalities to learn the information shared between them. However, that approach could fail…

Computer Vision and Pattern Recognition · Computer Science 2021-07-07 Yunze Liu , Qingnan Fan , Shanghang Zhang , Hao Dong , Thomas Funkhouser , Li Yi

Cross-modal alignment aims to map heterogeneous modalities into a shared latent space, as exemplified by models like CLIP, which benefit from large-scale image-text pretraining for strong recognition capabilities. However, when operating in…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Jiaxiang Liu , Yuan Wang , Jiawei Du , Joey Tianyi Zhou , Mingkun Xu , Zuozhu Liu

Humans perceive the world through multisensory integration, blending the information of different modalities to adapt their behavior. Contrastive learning offers an appealing solution for multimodal self-supervised learning. Indeed, by…

Machine Learning · Computer Science 2025-03-06 Benoit Dufumier , Javiera Castillo-Navarro , Devis Tuia , Jean-Philippe Thiran

Multimodal learning methods with targeted unimodal learning objectives have exhibited their superior efficacy in alleviating the imbalanced multimodal learning problem. However, in this paper, we identify the previously ignored gradient…

Computer Vision and Pattern Recognition · Computer Science 2024-05-29 Yake Wei , Di Hu

The key challenge in unaligned multimodal language sequences lies in effectively integrating information from various modalities to obtain a refined multimodal joint representation. Recently, the disentangle and fuse methods have achieved…

Computation and Language · Computer Science 2024-09-20 Fan Qian , Jiqing Han , Jianchen Li , Yongjun He , Tieran Zheng , Guibin Zheng

Multi-modal learning relates information across observation modalities of the same physical phenomenon to leverage complementary information. Most multi-modal machine learning methods require that all the modalities used for training are…

Machine Learning · Computer Science 2021-03-10 Vandana Rajan , Alessio Brutti , Andrea Cavallaro

Multimodal learning has seen remarkable progress, particularly with the emergence of large-scale pre-training across various modalities. However, most current approaches are built on the assumption of a deterministic, one-to-one alignment…

Machine Learning · Computer Science 2025-05-27 Sanghyuk Chun

Multimodality Representation Learning, as a technique of learning to embed information from different modalities and their correlations, has achieved remarkable success on a variety of applications, such as Visual Question Answering (VQA),…

Artificial Intelligence · Computer Science 2024-03-04 Muhammad Arslan Manzoor , Sarah Albarri , Ziting Xian , Zaiqiao Meng , Preslav Nakov , Shangsong Liang

Despite the impressive results achieved by multimodal large language models (MLLMs), their training typically relies on jointly curated multimodal data, requiring substantial human effort to construct multi-way aligned datasets and thereby…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Yan Li , Yunlong Deng , Yuewen Sun , Gongxu Luo , Kun Zhang , Guangyi Chen

Multimodal learning (MML) aims to jointly exploit the common priors of different modalities to compensate for their inherent limitations. However, existing MML methods often optimize a uniform objective for different modalities, leading to…

Machine Learning · Computer Science 2022-11-15 Yunfeng Fan , Wenchao Xu , Haozhao Wang , Junxiao Wang , Song Guo

Representation Learning is a significant and challenging task in multimodal learning. Effective modality representations should contain two parts of characteristics: the consistency and the difference. Due to the unified multimodal…

Computation and Language · Computer Science 2021-02-10 Wenmeng Yu , Hua Xu , Ziqi Yuan , Jiele Wu

Multimodal Dataset Distillation (MDD) seeks to condense large-scale image-text datasets into compact surrogates while retaining their effectiveness for cross-modal learning. Despite recent progress, existing MDD approaches often suffer from…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Xin Zhang , Ziruo Zhang , Jiawei Du , Zuozhu Liu , Joey Tianyi Zhou

Multimodal representations and continual learning are two areas closely related to human intelligence. The former considers the learning of shared representation spaces where information from different modalities can be compared and…

Computer Vision and Pattern Recognition · Computer Science 2021-04-20 Kai Wang , Luis Herranz , Joost van de Weijer

Deep generative models with latent variables have been used lately to learn joint representations and generative processes from multi-modal data. These two learning mechanisms can, however, conflict with each other and representations can…

Machine Learning · Computer Science 2023-01-24 Rogelio A. Mancisidor , Michael Kampffmeyer , Kjersti Aas , Robert Jenssen

Multimodal learning enables neural networks to integrate information from heterogeneous sources, but active learning in this setting faces distinct challenges. These include missing modalities, differences in modality difficulty, and…

Machine Learning · Computer Science 2026-04-01 Dustin Eisenhardt , Yunhee Jeong , Florian Buettner

Multimodal models integrating natural language and visual information have substantially improved generalization of representation models. However, their effectiveness significantly declines in real-world situations where certain modalities…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Jiajun Chen , Sai Cheng , Yutao Yuan , Yirui Zhang , Haitao Yuan , Peng Peng , Yi Zhong

Multimodal models often converge to a dominant-modality solution, in which a stronger, faster-converging modality overshadows weaker ones. This modality imbalance causes suboptimal performance. Existing methods attempt to balance different…

Multimedia · Computer Science 2026-03-19 Zechang Xiong , Da Li , Kexin Tang , Pengyuan Li , Wenkang Kong , Yulan Hu

Multimodal learning often encounters the under-optimized problem and may have worse performance than unimodal learning. Existing methods attribute this problem to the imbalanced learning between modalities and rebalance them through…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Shicai Wei , Chunbo Luo , Yang Luo

Multimodal learning often encounters the under-optimized problem and may perform worse than unimodal learning. Existing approaches attribute this issue to imbalanced learning across modalities and tend to address it through gradient…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Shicai Wei , Chunbo Luo , Yang Luo