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. 2407.05218
20
0

Effect of Rotation Angle in Self-Supervised Pre-training is Dataset-Dependent

21 June 2024
Amy Saranchuk
Michael Guerzhoy
ArXivPDFHTML
Abstract

Self-supervised learning for pre-training (SSP) can help the network learn better low-level features, especially when the size of the training set is small. In contrastive pre-training, the network is pre-trained to distinguish between different versions of the input. For example, the network learns to distinguish pairs (original, rotated) of images where the rotated image was rotated by angle θ\thetaθ vs. other pairs of images. In this work, we show that, when training using contrastive pre-training in this way, the angle θ\thetaθ and the dataset interact in interesting ways. We hypothesize, and give some evidence, that, for some datasets, the network can take "shortcuts" for particular rotation angles θ\thetaθ based on the distribution of the gradient directions in the input, possibly avoiding learning features other than edges, but our experiments do not seem to support that hypothesis. We demonstrate experiments on three radiology datasets. We compute the saliency map indicating which pixels were important in the SSP process, and compare the saliency map to the ground truth foreground/background segmentation. Our visualizations indicate that the effects of rotation angles in SSP are dataset-dependent. We believe the distribution of gradient orientations may play a role in this, but our experiments so far are inconclusive.

View on arXiv
Comments on this paper