Self-Supervised Learning Across Domains

TL;DR

This paper introduces a multi-task learning approach combining supervised and self-supervised learning for object recognition across diverse domains, enhancing generalization and adaptation capabilities.

Contribution

It proposes a novel method that integrates self-supervised signals with supervised learning to improve domain generalization in object recognition tasks.

Findings

The method achieves competitive results compared to complex domain adaptation techniques.

It effectively learns object shape concepts like orientation and parts.

Demonstrates success in predictive and partial domain adaptation scenarios.

Abstract

Human adaptability relies crucially on learning and merging knowledge from both supervised and unsupervised tasks: the parents point out few important concepts, but then the children fill in the gaps on their own. This is particularly effective, because supervised learning can never be exhaustive and thus learning autonomously allows to discover invariances and regularities that help to generalize. In this paper we propose to apply a similar approach to the problem of object recognition across domains: our model learns the semantic labels in a supervised fashion, and broadens its understanding of the data by learning from self-supervised signals on the same images. This secondary task helps the network to focus on object shapes, learning concepts like spatial orientation and part correlation, while acting as a regularizer for the classification task over multiple visual domains. Extensive experiments confirm our intuition and show that our multi-task method combining supervised and self-supervised knowledge shows competitive results with respect to more complex domain generalization and adaptation solutions. It also proves its potential in the novel and challenging predictive and partial domain adaptation scenarios.