A Study of the Generalizability of Self-Supervised Representations

TL;DR

This paper investigates the generalizability of self-supervised learning (SSL) representations compared to supervised learning (SL), revealing SSL's superior invariance and transferability across different datasets and tasks.

Contribution

It provides a comprehensive domain-based analysis of SSL versus SL representations, highlighting SSL's enhanced generalizability and invariance properties.

Findings

SSL representations are more generalizable than SL representations.

SSL exhibits better invariance properties.

SSL models maintain higher accuracy across diverse target datasets.

Abstract

Recent advancements in self-supervised learning (SSL) made it possible to learn generalizable visual representations from unlabeled data. The performance of Deep Learning models fine-tuned on pretrained SSL representations is on par with models fine-tuned on the state-of-the-art supervised learning (SL) representations. Irrespective of the progress made in SSL, its generalizability has not been studied extensively. In this article, we perform a deeper analysis of the generalizability of pretrained SSL and SL representations by conducting a domain-based study for transfer learning classification tasks. The representations are learned from the ImageNet source data, which are then fine-tuned using two types of target datasets: similar to the source dataset, and significantly different from the source dataset. We study generalizability of the SSL and SL-based models via their prediction accuracy as well as prediction confidence. In addition to this, we analyze the attribution of the final convolutional layer of these models to understand how they reason about the semantic identity of the data. We show that the SSL representations are more generalizable as compared to the SL representations. We explain the generalizability of the SSL representations by investigating its invariance property, which is shown to be better than that observed in the SL representations.