Saliency Can Be All You Need In Contrastive Self-Supervised Learning

TL;DR

This paper introduces a novel augmentation policy using salient image segmentation for contrastive self-supervised learning, demonstrating its effectiveness and potential as a sole augmentation method for segmentation tasks.

Contribution

It proposes using salient image segmentation as an augmentation in contrastive SSL, showing its effectiveness across multiple datasets and algorithms.

Findings

Salient segmentation improves SSL performance.

The technique is effective across various datasets.

Salient segmentation may suffice as the only augmentation.

Abstract

We propose an augmentation policy for Contrastive Self-Supervised Learning (SSL) in the form of an already established Salient Image Segmentation technique entitled Global Contrast based Salient Region Detection. This detection technique, which had been devised for unrelated Computer Vision tasks, was empirically observed to play the role of an augmentation facilitator within the SSL protocol. This observation is rooted in our practical attempts to learn, by SSL-fashion, aerial imagery of solar panels, which exhibit challenging boundary patterns. Upon the successful integration of this technique on our problem domain, we formulated a generalized procedure and conducted a comprehensive, systematic performance assessment with various Contrastive SSL algorithms subject to standard augmentation techniques. This evaluation, which was conducted across multiple datasets, indicated that the proposed technique indeed contributes to SSL. We hypothesize whether salient image segmentation may suffice as the only augmentation policy in Contrastive SSL when treating downstream segmentation tasks.