Self-Supervised Feature Enhancement: Applying Internal Pretext Task to Supervised Learning

Tianshu Xie

doi:10.1109/ACCESS.2022.3233104

Self-Supervised Feature Enhancement: Applying Internal Pretext Task to Supervised Learning

2023-01-01

1

OA

AI

DOI：10.1109/ACCESS.2022.3233104

Original

Original request for help

Save

Abstract

En 中文

Traditional self-supervised learning requires convolutional neural networks (CNNs) using external pretext tasks (i.e., image- or video-based tasks) to encode high-level semantic visual representations. In this paper, we show that feature transformations within CNNs can also be regarded as supervisory signals to construct the self-supervised task, called internal pretext task. And such a task can be applied for the enhancement of supervised learning. Specifically, we first transform the internal feature maps by discarding different channels, and then define an additional internal pretext task to identify the discarded channels. CNNs are trained to predict the joint labels generated by the combination of self-supervised labels and original labels. By doing so, we let CNNs know which channels are missing while classifying in the hope to mine richer feature information. Extensive experiments show that our approach is effective on various models and datasets. And it's worth noting that we only incur negligible computational overhead. Furthermore, our approach can also be compatible with other methods to get better results.

Keywords:

Task analysis

Training

Self-supervised learning

Visualization

Supervised learning

Semantics

Predictive models

Deep learning

classification

self-supervised learning

convolutional neural network

feature transformation

Self-Supervised Feature Enhancement: Applying Internal Pretext Task to Supervised Learning

Abstract

Journal

Organization