license: mit
pipeline_tag: image-classification
A Mutual Information Perspective on Multiple Latent Variable Generative Models for Positive View Generation
The model was presented in the paper A Mutual Information Perspective on Multiple Latent Variable Generative Models for Positive View Generation.
Abstract
In image generation, Multiple Latent Variable Generative Models (MLVGMs) employ multiple latent variables to gradually shape the final images, from global characteristics to finer and local details (e.g., StyleGAN, NVAE), emerging as powerful tools for diverse applications. Yet their generative dynamics remain only empirically observed, without a systematic understanding of each latent variable's impact. In this work, we propose a novel framework that quantifies the contribution of each latent variable using Mutual Information (MI) as a metric. Our analysis reveals that current MLVGMs often underutilize some latent variables, and provides actionable insights for their use in downstream applications. With this foundation, we introduce a method for generating synthetic data for Self-Supervised Contrastive Representation Learning (SSCRL). By leveraging the hierarchical and disentangled variables of MLVGMs, our approach produces diverse and semantically meaningful views without the need for real image data. Additionally, we introduce a Continuous Sampling (CS) strategy, where the generator dynamically creates new samples during SSCRL training, greatly increasing data variability. Our comprehensive experiments demonstrate the effectiveness of these contributions, showing that MLVGMs' generated views compete on par with or even surpass views generated from real data. This work establishes a principled approach to understanding and exploiting MLVGMs, advancing both generative modeling and self-supervised learning.
Code and Repository
The official GitHub repository for this project can be found at: https://github.com/SerezD/mi_ml_gen
Installation
To set up the environment and install the necessary dependencies, follow these steps:
# Dependencies Install
conda env create --file environment.yml
conda activate mi_ml_gen
# package install (in development mode)
conda develop ./mi_ml_gen
Generate Multiple Views
If your interest is to use the repository just for view generation, simply run the script:
python mi_ml_gen/src/scripts/view_generation.py --configuration ./conf.yaml --save_folder ./tmp/
Examples of valid configurations are:
mi_ml_gen/configurations/view_generation/bigbigan.yaml
mi_ml_gen/configurations/view_generation/stylegan.yaml.
For example, they allow to generate things like:
Citation
If you find our work useful, please consider citing our paper:
@article{
serez2025a,
title={A Mutual Information Perspective on Multiple Latent Variable Generative Models for Positive View Generation},
author={Dario Serez and Marco Cristani and Alessio Del Bue and Vittorio Murino and Pietro Morerio},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2025},
url={https://openreview.net/forum?id=uaj8ZL2PtK},
note={}
}