paper-with-me

Papers

Learning Multimodal Latent Generative Models with Energy-Based Prior

2024-09-30 · Shiyu Yuan, Jiali Cui, Hanao Li, Tian Han

Multimodal generative models have recently gained significant attention for their ability to learn representations across various modalities, enhancing joint and cross-generation coherence. However, most existing works use standard Gaussian or Laplacian distributions as priors, which may struggle to capture the diverse information inherent in multiple data types due to their unimodal and less informative nature. Energy-based models (EBMs), known for their expressiveness and flexibility across various tasks, have yet to be thoroughly explored in the context of multimodal generative models. In this paper, we propose a novel framework that integrates the multimodal latent generative model with the EBM. Both models can be trained jointly through a variational scheme. This approach results in a more expressive and informative prior, better-capturing of information across multiple modalities. Our experiments validate the proposed model, demonstrating its superior generation coherence.

📄 PDF Abstract BibTeX arXiv:2409.19862

Code (1)

syyuan2021/Learning-Multimodal-Latent-Generative-Models-with-EBM-project 공식 구현

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
EBM 설명 없음

Similar Papers 제목 키워드 기반

Learning Multimodal Latent Space with EBM Prior and MCMC Inference

2024-08-20 · Shiyu Yuan, Carlo Lipizzi, Tian Han

Multimodal generative models are crucial for various applications. We propose an approach that combines an expressive energy-based model (EBM) prior with Markov Chain Monte Carlo (MCMC) inference in the latent space for …

multimodal generation

An Energy-Based Prior for Generative Saliency

2022-04-19 · Jing Zhang, Jianwen Xie, Nick Barnes, Ping Li

We propose a novel generative saliency prediction framework that adopts an informative energy-based model as a prior distribution. The energy-based prior model is defined on the latent space of a saliency generator netwo…

object-detectionObject DetectionRGB-D Salient Object DetectionSaliency Prediction+2

Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction

2021-12-27 · NeurIPS 2021 12 · Jing Zhang, Jianwen Xie, Nick Barnes, Ping Li

Vision transformer networks have shown superiority in many computer vision tasks. In this paper, we take a step further by proposing a novel generative vision transformer with latent variables following an informative en…

object-detectionObject DetectionRGB-D Salient Object DetectionSaliency Prediction+2

Improving VAE generations of multimodal data through data-dependent conditional priors

2019-11-25 · Frantzeska Lavda, Magda Gregorová, Alexandros Kalousis

One of the major shortcomings of variational autoencoders is the inability to produce generations from the individual modalities of data originating from mixture distributions. This is primarily due to the use of a simpl…

Learning Multimodal Energy-Based Model with Multimodal Variational Auto-Encoder via MCMC Revision

2026-05-01 · Jiali Cui, Zhiqiang Lao, Heather Yu arxiv

Energy-based models (EBMs) are a flexible class of deep generative models and are well-suited to capture complex dependencies in multimodal data. However, learning multimodal EBM by maximum likelihood requires Markov Cha…