Decoupled self-supervised label augmentation for fully-supervised image classification

doi:10.1016/j.knosys.2021.107605

Decoupled self-supervised label augmentation for fully-supervised image classification

2022-01-01

9

PRE

AI

DOI：10.1016/j.knosys.2021.107605

Original

Original request for help

Save

Abstract

En 中文

Self-supervised label augmentation has emerged as an effective means to overcome the data scarcity problem for supervised vision tasks. Existing rotation-based self-supervised label augmentation methods either impose or relax the rotation invariance constraint on the primary classifier, which omit necessary supervisory information and may degrade the classification performance depending on the given working data. To overcome this problem, we propose a decoupled self-supervised label augmentation method to enhance the feature representation for fully-supervised image classification. Experimental results on diverse datasets demonstrate that the proposed method consistently outperforms state-of-the-art data augmentation methods. The proposed method is also complementary to conventional data augmentation methods, such as AutoAugment and Fast AutoAugment. (C) 2021 Elsevier B.V. All rights reserved.

Keywords:

Self-supervised label augmentation

Image classification

Multi-task learning

Decoupled self-supervised label augmentation for fully-supervised image classification

Abstract

Journal

Organization