English
Related papers

Related papers: OVA-IB: One vs All Information Bottleneck for Mult…

200 papers

We address the question of characterizing and finding optimal representations for supervised learning. Traditionally, this question has been tackled using the Information Bottleneck, which compresses the inputs while retaining information…

Machine Learning · Computer Science 2021-07-19 Yann Dubois , Douwe Kiela , David J. Schwab , Ramakrishna Vedantam

Multi-modal semantic understanding requires integrating information from different modalities to extract users' real intention behind words. Most previous work applies a dual-encoder structure to separately encode image and text, but fails…

Computation and Language · Computer Science 2024-03-12 Ming Zhang , Ke Chang , Yunfang Wu

Multimodal sentiment analysis has received significant attention across diverse research domains. Despite advancements in algorithm design, existing approaches suffer from two critical limitations: insufficient learning of…

Artificial Intelligence · Computer Science 2025-11-04 Huiting Huang , Tieliang Gong , Kai He , Jialun Wu , Erik Cambria , Mengling Feng

In this paper, we propose a unified information theoretic framework for learning-motivated methods aimed at odometry estimation, a crucial component of many robotics and vision tasks such as navigation and virtual reality where relative…

Computer Vision and Pattern Recognition · Computer Science 2022-08-16 Sen Zhang , Jing Zhang , Dacheng Tao

Multimodal learning seeks to integrate information from heterogeneous sources, where signals may be shared across modalities, specific to individual modalities, or emerge only through their interaction. While self-supervised multimodal…

Machine Learning · Computer Science 2026-02-17 Carolin Cissee , Raneen Younis , Zahra Ahmadi

Contrastive learning methods, such as CLIP, leverage naturally paired data-for example, images and their corresponding text captions-to learn general representations that transfer efficiently to downstream tasks. While such approaches are…

Machine Learning · Computer Science 2024-11-05 Adriel Saporta , Aahlad Puli , Mark Goldstein , Rajesh Ranganath

We propose Domain-Conditioned Meta-Contrastive Learning, a framework for improving the cross-domain generalization of vision-language models. While contrastive models such as CLIP achieve strong performance through large-scale training,…

Optimization and Control · Mathematics 2026-03-31 Merham Fouladvand , Peuroly Batra

Multi-view learning is widely applied to real-life datasets, such as multiple omics biological data, but it often suffers from both missing views and missing labels. Prior probabilistic approaches addressed the missing view problem by using…

Machine Learning · Computer Science 2025-08-18 Yiyang Shen , Weiran Wang

Invariant risk minimization (IRM) has recently emerged as a promising alternative for domain generalization. Nevertheless, the loss function is difficult to optimize for nonlinear classifiers and the original optimization objective could…

Machine Learning · Computer Science 2022-03-22 Bo Li , Yifei Shen , Yezhen Wang , Wenzhen Zhu , Colorado J. Reed , Jun Zhang , Dongsheng Li , Kurt Keutzer , Han Zhao

Learning invariant representations is a critical first step in a number of machine learning tasks. A common approach corresponds to the so-called information bottleneck principle in which an application dependent function of mutual…

Machine Learning · Computer Science 2021-02-17 Aditya Kumar Akash , Vishnu Suresh Lokhande , Sathya N. Ravi , Vikas Singh

Unified multimodal large language models (MLLMs) aim to unify image understanding and image generation within a single framework, where a shared visual tokenizer serves as the sole interface that maps high-dimensional images into a limited…

Machine Learning · Computer Science 2026-04-07 Lv Tang , Tianyi Zheng , Bo Li , Xingyu Li

Recently, contrastive learning approaches (e.g., CLIP (Radford et al., 2021)) have received huge success in multimodal learning, where the model tries to minimize the distance between the representations of different views (e.g., image and…

Machine Learning · Computer Science 2023-04-10 Yunwei Ren , Yuanzhi Li

Fine-tuning large-scale pretrained models has led to tremendous progress in well-studied modalities such as vision and NLP. However, similar gains have not been observed in many other modalities due to a lack of relevant pretrained models.…

Machine Learning · Computer Science 2023-03-21 Junhong Shen , Liam Li , Lucio M. Dery , Corey Staten , Mikhail Khodak , Graham Neubig , Ameet Talwalkar

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

Deep neural networks (DNNs) have achieved significant success in various applications with large-scale and balanced data. However, data in real-world visual recognition are usually long-tailed, bringing challenges to efficient training and…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Yifan Lan , Xin Cai , Jun Cheng , Shan Tan

Existing image-text modality alignment in Vision Language Models (VLMs) treats each text token equally in an autoregressive manner. Despite being simple and effective, this method results in sub-optimal cross-modal alignment by…

Computer Vision and Pattern Recognition · Computer Science 2024-11-06 Xin Xiao , Bohong Wu , Jiacong Wang , Chunyuan Li , Xun Zhou , Haoyuan Guo

Continual learning is essential for adapting models to new tasks while retaining previously acquired knowledge. While existing approaches predominantly focus on uni-modal data, multi-modal learning offers substantial benefits by utilizing…

Machine Learning · Computer Science 2025-11-11 Evelyn Chee , Wynne Hsu , Mong Li Lee

Multimodal learning combines information from multiple data modalities to improve predictive performance. However, modalities often contribute unequally and in a data dependent way, making it unclear which data modalities are genuinely…

Machine Learning · Statistics 2026-02-03 Mathew Chandy , Michael Johnson , Judong Shen , Devan V. Mehrotra , Hua Zhou , Jin Zhou , Xiaowu Dai

Multi-modal contrastive models such as CLIP achieve state-of-the-art performance in zero-shot classification by embedding input images and texts on a joint representational space. Recently, a modality gap has been reported in two-encoder…

Computer Vision and Pattern Recognition · Computer Science 2024-06-10 Abrar Fahim , Alex Murphy , Alona Fyshe

Multi-view clustering can make use of multi-source information for unsupervised clustering. Most existing methods focus on learning a fused representation matrix, while ignoring the influence of private information and noise. To address…

Machine Learning · Computer Science 2023-03-02 Wenbiao Yan , Jihua Zhu , Yiyang Zhou , Yifei Wang , Qinghai Zheng