English
Related papers

Related papers: Multi-Modal Representation Learning with Self-Adap…

200 papers

Learning with few labeled data is a key challenge for visual recognition, as deep neural networks tend to overfit using a few samples only. One of the Few-shot learning methods called metric learning addresses this challenge by first…

Computer Vision and Pattern Recognition · Computer Science 2022-03-28 Li Ke , Meng Pan , Weigao Wen , Dong Li

As medical diagnoses increasingly leverage multimodal data, machine learning models are expected to effectively fuse heterogeneous information while remaining robust to missing modalities. In this work, we propose a novel multimodal…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Yi Gu , Kuniaki Saito , Jiaxin Ma

We propose an approach to self-supervised representation learning based on maximizing mutual information between features extracted from multiple views of a shared context. For example, one could produce multiple views of a local…

Machine Learning · Computer Science 2019-07-09 Philip Bachman , R Devon Hjelm , William Buchwalter

Real-world vision based applications require fine-grained classification for various area of interest like e-commerce, mobile applications, warehouse management, etc. where reducing the severity of mistakes and improving the classification…

Computer Vision and Pattern Recognition · Computer Science 2023-03-01 Sudeep Kumar Sahoo , Sathish Chalasani , Abhishek Joshi , Kiran Nanjunda Iyer

Human perception integrates multiple modalities, such as vision, hearing, and language, into a unified understanding of the surrounding reality. While recent multimodal models have achieved significant progress by aligning pairs of…

Computer Vision and Pattern Recognition · Computer Science 2025-02-13 Giordano Cicchetti , Eleonora Grassucci , Luigi Sigillo , Danilo Comminiello

Multi-view (or -modality) representation learning aims to understand the relationships between different view representations. Existing methods disentangle multi-view representations into consistent and view-specific representations by…

Computer Vision and Pattern Recognition · Computer Science 2023-08-07 Guanzhou Ke , Yang Yu , Guoqing Chao , Xiaoli Wang , Chenyang Xu , Shengfeng He

Image-Text Retrieval (ITR) is challenging in bridging visual and lingual modalities. Contrastive learning has been adopted by most prior arts. Except for limited amount of negative image-text pairs, the capability of constrastive learning…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Haoran Wang , Dongliang He , Wenhao Wu , Boyang Xia , Min Yang , Fu Li , Yunlong Yu , Zhong Ji , Errui Ding , Jingdong Wang

In this paper, we propose a new approach to learn multimodal multilingual embeddings for matching images and their relevant captions in two languages. We combine two existing objective functions to make images and captions close in a joint…

Computation and Language · Computer Science 2020-11-02 Alireza Mohammadshahi , Remi Lebret , Karl Aberer

In a wide range of multimodal tasks, contrastive learning has become a particularly appealing approach since it can successfully learn representations from abundant unlabeled data with only pairing information (e.g., image-caption or…

Machine Learning · Computer Science 2023-10-31 Paul Pu Liang , Zihao Deng , Martin Ma , James Zou , Louis-Philippe Morency , Ruslan Salakhutdinov

Recently, as an effective way of learning latent representations, contrastive learning has been increasingly popular and successful in various domains. The success of constrastive learning in single-label classifications motivates us to…

Computer Vision and Pattern Recognition · Computer Science 2021-07-27 Son D. Dao , Ethan Zhao , Dinh Phung , Jianfei Cai

In e-commerce search, personalized retrieval is a crucial technique for improving user shopping experience. Recent works in this domain have achieved significant improvements by the representation learning paradigm, e.g., embedding-based…

Information Retrieval · Computer Science 2023-07-11 Longbin Li , Chao Zhang , Sen Li , Yun Zhong , Qingwen Liu , Xiaoyi Zeng

Multimodal learning integrates data from diverse sensors to effectively harness information from different modalities. However, recent studies reveal that joint learning often overfits certain modalities while neglecting others, leading to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Feng Yu , Xiangyu Wu , Yang Yang , Jianfeng Lu

The cataloging of product listings is a fundamental problem for most e-commerce platforms. Despite promising results obtained by unimodal-based methods, it can be expected that their performance can be further boosted by the consideration…

Computer Vision and Pattern Recognition · Computer Science 2020-08-17 Ye Bi , Shuo Wang , Zhongrui Fan

Learning high-quality feature embeddings efficiently and effectively is critical for the performance of web-scale machine learning systems. A typical model ingests hundreds of features with vocabularies on the order of millions to billions…

Machine Learning · Computer Science 2024-06-19 Benjamin Coleman , Wang-Cheng Kang , Matthew Fahrbach , Ruoxi Wang , Lichan Hong , Ed H. Chi , Derek Zhiyuan Cheng

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

Medical multimodal representation learning aims to integrate heterogeneous data into unified patient representations to support clinical outcome prediction. However, real-world medical datasets commonly contain systematic biases from…

Machine Learning · Computer Science 2026-05-19 Xiaoguang Zhu , Linxiao Gong , Lianlong Sun , Yang Liu , Haoyu Wang , Jing Liu

Multimodal learning enhances the performance of various machine learning tasks by leveraging complementary information across different modalities. However, existing methods often learn multimodal representations that retain substantial…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Tong Zhang , Shu Shen , C. L. Philip Chen

Self-supervised visual representation methods are closing the gap with supervised learning performance. These methods rely on maximizing the similarity between embeddings of related synthetic inputs created through data augmentations. This…

Machine Learning · Computer Science 2023-06-09 Alexandre Devillers , Mathieu Lefort

Alignment and uniformity are fundamental principles within the domain of contrastive learning. In recommender systems, prior work has established that optimizing the Bayesian Personalized Ranking (BPR) loss contributes to the objectives of…

Information Retrieval · Computer Science 2025-08-05 Xin Zhou , Yongjie Wang , Zhiqi Shen

In deepfake detection, the varying degrees of compression employed by social media platforms pose significant challenges for model generalization and reliability. Although existing methods have progressed from single-modal to multimodal…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Ching-Yi Lai , Chih-Yu Jian , Pei-Cheng Chuang , Chia-Ming Lee , Chih-Chung Hsu , Chiou-Ting Hsu , Chia-Wen Lin