Year: 2022
Type: preprint
Abstract: Vision transformers require a huge amount of labeled data to outperform convolutional neural networks. However, labeling a huge dataset is a very expensive process. Self-supervised learning techniques alleviate this problem by learning features similar to supervised learning in an unsupervised way. In this paper, we propose a self-supervised technique PatchRot that is crafted for vision transformers. PatchRot rotates images and image patches and trains the network to predict the rotation angles. The network learns to extract both global and local features from an image. Our extensive experiments on different datasets showcase PatchRot training learns rich features which outperform supervised learning and compared baseline.
Source: arXiv (Cornell University)
Authors: Chhabra, Sachin, Dutta, Prabal Bijoy, Venkateswara, Hemanth, Li, Baoxin
Institutions: Arizona State University, Georgia State University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Office of Naval Research
OpenAlex ID: W4307783012