• Home
  • Search
  • Can Generative Models Improve Self-Supervised Representation Learning?
  • Cite Icon1
  • https://doi.org/10.1609/aaai.v39i2.32174Copy DOI Icon

Can Generative Models Improve Self-Supervised Representation Learning?

Show More
  • Abstract
  • Literature Map
  • Citations
  • Similar Papers
Abstract

The rapid advancement in self-supervised representation learning has highlighted its potential to leverage unlabeled data for learning rich visual representations. However, the existing techniques, particularly those employing different augmentations of the same image, often rely on a limited set of simple transformations that cannot fully capture variations in the real world. This constrains the diversity and quality of samples, which leads to sub-optimal representations. In this paper, we introduce a framework that enriches the self-supervised learning (SSL) paradigm by utilizing generative models to produce semantically consistent image augmentations. By directly conditioning generative models on a source image, our method enables the generation of diverse augmentations while maintaining the semantics of the source image, thus offering a richer set of data for SSL. Our extensive experimental results on various joint-embedding SSL techniques demonstrate that our framework significantly enhances the quality of learned visual representations by up to 10% Top-1 accuracy in downstream tasks. This research demonstrates that incorporating generative models into the joint-embedding SSL workflow opens new avenues for exploring the potential of synthetic data. This development paves the way for more robust and versatile representation learning techniques.

Similar Papers
  • Conference Article
  • Citations2

A Novel Multi-Task Self-Supervised Representation Learning Paradigm

  • May 28, 2021
  • Control theory & applications
  • Yinggang Li +5
  • Conference Article
  • Citations16

A Novel Solution for EEG-based Emotion Recognition

  • Oct 13, 2021
  • Zhuofan Xie +2
  • Preprint Article

Self-Supervised Learning Principles Challenges and Emerging Directions

  • Feb 24, 2025
  • Preprints.org
  • Jenifer Nadine
  • Book Chapter
  • Citations7

CaSS: A Channel-Aware Self-supervised Representation Learning Framework for Multivariate Time Series Classification

  • Jan 01, 2022
  • Yijiang Chen +4
  • Research Article
  • Citations177

Self-supervised representation learning from 12-lead ECG data

  • Dec 18, 2021
  • Computers in Biology and Medicine
  • Temesgen Mehari +1
  • Research Article
  • Citations7

MLVICX: Multi-Level Variance-Covariance Exploration for Chest X-Ray Self-Supervised Representation Learning.

  • Dec 01, 2024
  • IEEE journal of biomedical and health informatics
  • Azad Singh +2
  • Dissertation

Learning visual representations without human supervision

  • Jan 01, 2023
  • Jiahao Xie
  • Research Article

Abstract 5059: Self-supervised representation learning of somatic mutational data

  • Apr 21, 2025
  • Cancer Research
  • Marzieh Haghighi +2
  • Research Article
  • Citations14

Benchmarking Self-Supervised Contrastive Learning Methods for Image-Based Plant Phenotyping

  • Jan 01, 2023
  • Plant Phenomics
  • Franklin C Ogidi +2
  • PDF
  • Research Article

Enhancing self-supervised visual representation learning through adversarially generated examples

  • May 14, 2025
  • Neural Computing and Applications
  • Mintae Kang +1
  • Conference Article
  • Citations58

LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech

  • Aug 30, 2021
  • Solène Evain +17
  • Conference Article
  • Citations12

Conformer-Based Self-Supervised Learning For Non-Speech Audio Tasks

  • May 23, 2022
  • Sangeeta Srivastava +6
  • Conference Article
  • Citations16

Tricycle: Audio Representation Learning from Sensor Network Data Using Self-Supervision

  • Oct 01, 2019
  • Mark Cartwright +3
  • Research Article
  • Citations20

Self-supervised visual learning in the low-data regime: A comparative evaluation

  • Mar 01, 2025
  • Neurocomputing
  • Sotirios Konstantakos +6
  • Research Article
  • Citations1

Self-supervised representation learning on gene expression data

  • Oct 01, 2025
  • Bioinformatics
  • Kevin Dradjat +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.