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

TL;DR

This paper introduces an internal pretext task for CNNs that enhances supervised learning by transforming internal feature maps, enabling the network to identify discarded channels and learn richer features with minimal computational overhead.

Contribution

The paper proposes a novel internal pretext task that uses feature transformations within CNNs to improve supervised learning without external pretext tasks.

Findings

Effective across various models and datasets

Achieves improved feature representations

Negligible additional computational cost

Abstract

Traditional self-supervised learning requires 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 \emph{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.