English
Related papers

Related papers: With Limited Data for Multimodal Alignment, Let th…

200 papers

Data scarcity is a major limiting factor for applying modern machine learning techniques to clinical tasks. Although sufficient data exists for some well-studied medical tasks, there remains a long tail of clinically relevant tasks with…

Computer Vision and Pattern Recognition · Computer Science 2024-08-16 Stefano Woerner , Christian F. Baumgartner

This paper investigates how to better leverage large-scale pre-trained uni-modal models to further enhance discriminative multi-modal learning. Even when fine-tuned with only uni-modal data, these models can outperform previous multi-modal…

Computer Vision and Pattern Recognition · Computer Science 2023-10-10 Chenzhuang Du , Yue Zhao , Chonghua Liao , Jiacheng You , Jie Fu , Hang Zhao

Hierarchical clustering is a popular unsupervised data analysis method. For many real-world applications, we would like to exploit prior information about the data that imposes constraints on the clustering hierarchy, and is not captured by…

Data Structures and Algorithms · Computer Science 2018-07-17 Vaggos Chatziafratis , Rad Niazadeh , Moses Charikar

The Segment Anything Model (SAM) has demonstrated remarkable capabilities of scaled-up segmentation models, enabling zero-shot generalization across a variety of domains. By leveraging large-scale foundational models as pre-trained models,…

Computer Vision and Pattern Recognition · Computer Science 2023-08-29 Weijia Feng , Lingting Zhu , Lequan Yu

State-of-the-art deep learning algorithms yield remarkable results in many visual recognition tasks. However, they still fail to provide satisfactory results in scarce data regimes. To a certain extent this lack of data can be compensated…

Computer Vision and Pattern Recognition · Computer Science 2018-11-26 Frederik Pahde , Oleksiy Ostapenko , Patrick Jähnichen , Tassilo Klein , Moin Nabi

Multimodal federated learning in real-world settings often encounters incomplete and heterogeneous data across clients. This results in misaligned local feature representations that limit the effectiveness of model aggregation. Unlike prior…

Machine Learning · Computer Science 2025-10-28 Duong M. Nguyen , Trong Nghia Hoang , Thanh Trung Huynh , Quoc Viet Hung Nguyen , Phi Le Nguyen

Cross-modal alignment is crucial for multimodal representation fusion due to the inherent heterogeneity between modalities. While Transformer-based methods have shown promising results in modeling inter-modal relationships, their quadratic…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Yan Li , Yifei Xing , Xiangyuan Lan , Xin Li , Haifeng Chen , Dongmei Jiang

Model merging (e.g., via interpolation or task arithmetic) fuses multiple models trained on different tasks to generate a multi-task solution. The technique has been proven successful in previous studies, where the models are trained on…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Yi-Lin Sung , Linjie Li , Kevin Lin , Zhe Gan , Mohit Bansal , Lijuan Wang

With the development of cheap image sensors, the amount of available image data have increased enormously, and the possibility of using crowdsourced collection methods has emerged. This calls for development of ways to handle all these…

Computer Vision and Pattern Recognition · Computer Science 2021-03-25 Gabrielle Flood , David Gillsjö , Patrik Persson , Anders Heyden , Kalle Åström

Large-scale multimodal representation learning successfully optimizes for zero-shot transfer at test time. Yet the standard pretraining paradigm (contrastive learning on large amounts of image-text data) does not explicitly encourage…

Computer Vision and Pattern Recognition · Computer Science 2024-11-25 Karsten Roth , Zeynep Akata , Dima Damen , Ivana Balažević , Olivier J. Hénaff

We present ImageBind, an approach to learn a joint embedding across six different modalities - images, text, audio, depth, thermal, and IMU data. We show that all combinations of paired data are not necessary to train such a joint…

Computer Vision and Pattern Recognition · Computer Science 2023-06-01 Rohit Girdhar , Alaaeldin El-Nouby , Zhuang Liu , Mannat Singh , Kalyan Vasudev Alwala , Armand Joulin , Ishan Misra

One-class classification refers to approaches of learning using data from a single class only. In this paper, we propose a deep learning one-class classification method suitable for multimodal data, which relies on two convolutional…

Machine Learning · Computer Science 2023-09-26 Firas Laakom , Fahad Sohrab , Jenni Raitoharju , Alexandros Iosifidis , Moncef Gabbouj

Collecting annotated data for semantic segmentation is time-consuming and hard to scale up. In this paper, we for the first time propose a unified framework, termed as Multi-Dataset Pretraining, to take full advantage of the fragmented…

Computer Vision and Pattern Recognition · Computer Science 2021-06-09 Bowen Shi , Xiaopeng Zhang , Haohang Xu , Wenrui Dai , Junni Zou , Hongkai Xiong , Qi Tian

We present UniBind, a flexible and efficient approach that learns a unified representation space for seven diverse modalities -- images, text, audio, point cloud, thermal, video, and event data. Existing works, eg., ImageBind, treat the…

Computer Vision and Pattern Recognition · Computer Science 2024-03-20 Yuanhuiyi Lyu , Xu Zheng , Jiazhou Zhou , Lin Wang

Multimodal contrastive learning is a methodology for linking different data modalities; the canonical example is linking image and text data. The methodology is typically framed as the identification of a set of encoders, one for each…

Machine Learning · Statistics 2025-06-02 Ricardo Baptista , Andrew M. Stuart , Son Tran

From medical diagnosis to autonomous vehicles, critical applications rely on the integration of multiple heterogeneous data modalities. Multimodal Variational Autoencoders offer versatile and scalable methods for generating unobserved…

Machine Learning · Computer Science 2025-02-07 Agathe Senellart , Stéphanie Allassonnière

A core task in multi-modal learning is to integrate information from multiple feature spaces (e.g., text and audio), offering modality-invariant essential representations of data. Recent research showed that, classical tools such as {\it…

Machine Learning · Computer Science 2024-10-02 Subash Timilsina , Sagar Shrestha , Xiao Fu

In scientific machine learning, regression networks have been recently applied to approximate solution maps (e.g., potential-ground state map of Schr\"odinger equation). In this paper, we aim to reduce the generalization error without…

Numerical Analysis · Mathematics 2021-02-16 Zhihan Li , Yuwei Fan , Lexing Ying

Unified multimodal embedding spaces underpin practical applications such as cross-modal retrieval and zero-shot recognition. In many real deployments, however, supervision is available only for a small subset of modality pairs (e.g.,…

Artificial Intelligence · Computer Science 2026-05-19 Jincheng Xie , Xingchen Xiao , Runheng Liu , Zhongyi Huang , Yu Zheng , Heyan Huang

Learning shared representations is a primary area of multimodal representation learning. The current approaches to achieve a shared embedding space rely heavily on paired samples from each modality, which are significantly harder to obtain…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Amitai Yacobi , Nir Ben-Ari , Ronen Talmon , Uri Shaham