English
Related papers

Related papers: Multimodal Generative Models for Scalable Weakly-S…

200 papers

Devising deep latent variable models for multi-modal data has been a long-standing theme in machine learning research. Multi-modal Variational Autoencoders (VAEs) have been a popular generative model class that learns latent representations…

Machine Learning · Statistics 2024-09-25 Marcel Hirt , Domenico Campolo , Victoria Leong , Juan-Pablo Ortega

A number of variational autoencoders (VAEs) have recently emerged with the aim of modeling multimodal data, e.g., to jointly model images and their corresponding captions. Still, multimodal VAEs tend to focus solely on a subset of the…

Machine Learning · Computer Science 2022-06-10 Adrián Javaloy , Maryam Meghdadi , Isabel Valera

Building scalable models to learn from diverse, multimodal data remains an open challenge. For vision-language data, the dominant approaches are based on contrastive learning objectives that train a separate encoder for each modality. While…

Computer Vision and Pattern Recognition · Computer Science 2022-10-24 Xinyang Geng , Hao Liu , Lisa Lee , Dale Schuurmans , Sergey Levine , Pieter Abbeel

Generative models often incur the catastrophic forgetting problem when they are used to sequentially learning multiple tasks, i.e., lifelong generative learning. Although there are some endeavors to tackle this problem, they suffer from…

Machine Learning · Computer Science 2022-01-20 Libo Huang , Zhulin An , Xiang Zhi , Yongjun Xu

Multimodal variational autoencoders (VAEs) are widely used for weakly supervised generative learning with multiple modalities. Predominant methods aggregate unimodal inference distributions using either a product of experts (PoE), a mixture…

Machine Learning · Computer Science 2026-04-01 Huyen Vo , Isabel Valera

Multimodal Language Analysis is a demanding area of research, since it is associated with two requirements: combining different modalities and capturing temporal information. During the last years, several works have been proposed in the…

Computation and Language · Computer Science 2022-01-10 Panagiotis Koromilas , Theodoros Giannakopoulos

Multi-modal generative models represent an important family of deep models, whose goal is to facilitate representation learning on data with multiple views or modalities. However, current deep multi-modal models focus on the inference of…

Computer Vision and Pattern Recognition · Computer Science 2020-12-25 Mihee Lee , Vladimir Pavlovic

Multimodal learning for generative models often refers to the learning of abstract concepts from the commonality of information in multiple modalities, such as vision and language. While it has proven effective for learning generalisable…

Machine Learning · Computer Science 2021-04-22 Yuge Shi , Brooks Paige , Philip H. S. Torr , N. Siddharth

Missing input sequences are common in medical imaging data, posing a challenge for deep learning models reliant on complete input data. In this work, inspired by MultiMAE [2], we develop a masked autoencoder (MAE) paradigm for multi-modal,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Ayhan Can Erdur , Christian Beischl , Daniel Scholz , Jiazhen Pan , Benedikt Wiestler , Daniel Rueckert , Jan C Peeken

Learning latent representations that are simultaneously expressive, geometrically well-structured, and reliably calibrated remains a central challenge for Variational Autoencoders (VAEs). Standard VAEs typically assume a diagonal Gaussian…

Machine Learning · Computer Science 2025-12-02 Mehmet Can Yavuz

Variational autoencoder (VAE) is a widely used generative model for learning latent representations. Burda et al. in their seminal paper showed that learning capacity of VAE is limited by over-pruning. It is a phenomenon where a significant…

Machine Learning · Computer Science 2020-08-10 Rayyan Ahmad Khan , Muhammad Umer Anwaar , Martin Kleinsteuber

Learning interpretable and disentangled representations of data is a key topic in machine learning research. Variational Autoencoder (VAE) is a scalable method for learning directed latent variable models of complex data. It employs a clear…

Machine Learning · Computer Science 2020-06-04 Andriy Serdega , Dae-Shik Kim

Machine learning systems are often deployed in domains that entail data from multiple modalities, for example, phenotypic and genotypic characteristics describe patients in healthcare. Previous works have developed multimodal variational…

Machine Learning · Computer Science 2022-04-12 Jannik Wolff , Tassilo Klein , Moin Nabi , Rahul G. Krishnan , Shinichi Nakajima

In this work, we focus on unsupervised vision-language-action mapping in the area of robotic manipulation. Recently, multiple approaches employing pre-trained large language and vision models have been proposed for this task. However, they…

Robotics · Computer Science 2025-05-29 Gabriela Sejnova , Michal Vavrecka , Karla Stepanova

Increasingly many real world tasks involve data in multiple modalities or views. This has motivated the development of many effective algorithms for learning a common latent space to relate multiple domains. However, most existing…

Computer Vision and Pattern Recognition · Computer Science 2017-11-17 Tanmoy Mukherjee , Makoto Yamada , Timothy M. Hospedales

Learning from heterogeneous data poses challenges such as combining data from various sources and of different types. Meanwhile, heterogeneous data are often associated with missingness in real-world applications due to heterogeneity and…

Machine Learning · Computer Science 2021-02-26 Yu Gong , Hossein Hajimirsadeghi , Jiawei He , Thibaut Durand , Greg Mori

We introduce the concept of a Modular Autoencoder (MAE), capable of learning a set of diverse but complementary representations from unlabelled data, that can later be used for supervised tasks. The learning of the representations is…

Machine Learning · Computer Science 2015-11-24 Henry W J Reeve , Gavin Brown

We describe a novel weakly supervised deep learning framework that combines both the discriminative and generative models to learn meaningful representation in the multiple instance learning (MIL) setting. MIL is a weakly supervised…

Machine Learning · Computer Science 2018-07-09 Shabnam Ghaffarzadegan

We extend variational autoencoders (VAEs) to collaborative filtering for implicit feedback. This non-linear probabilistic model enables us to go beyond the limited modeling capacity of linear factor models which still largely dominate…

Machine Learning · Statistics 2018-02-19 Dawen Liang , Rahul G. Krishnan , Matthew D. Hoffman , Tony Jebara

Integrating physics models within machine learning models holds considerable promise toward learning robust models with improved interpretability and abilities to extrapolate. In this work, we focus on the integration of incomplete physics…

Machine Learning · Computer Science 2021-10-28 Naoya Takeishi , Alexandros Kalousis