ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2312.01187
19
1

SASSL: Enhancing Self-Supervised Learning via Neural Style Transfer

2 December 2023
Renan A. Rojas-Gomez
Karan Singhal
Ali Etemad
Alex Bijamov
Warren Morningstar
Philip Mansfield
ArXivPDFHTML
Abstract

Existing data augmentation in self-supervised learning, while diverse, fails to preserve the inherent structure of natural images. This results in distorted augmented samples with compromised semantic information, ultimately impacting downstream performance. To overcome this, we propose SASSL: Style Augmentations for Self Supervised Learning, a novel augmentation technique based on Neural Style Transfer. SASSL decouples semantic and stylistic attributes in images and applies transformations exclusively to the style while preserving content, generating diverse samples that better retain semantics. Our technique boosts top-1 classification accuracy on ImageNet by up to 2%\%% compared to established self-supervised methods like MoCo, SimCLR, and BYOL, while achieving superior transfer learning performance across various datasets.

View on arXiv
Comments on this paper