Cross-domain Self-supervised Learning for Domain Adaptation with Few Source Labels

TL;DR

This paper introduces a cross-domain self-supervised learning method designed for domain adaptation scenarios with limited labeled source data, effectively learning discriminative, domain-invariant features to improve target domain performance.

Contribution

It proposes a novel self-supervised learning approach that enhances domain adaptation with few source labels by capturing visual similarities and cross-domain feature matching.

Findings

Significantly improves target accuracy with few source labels.

Effective on standard benchmark datasets.

Helpful in classical domain adaptation scenarios.

Abstract

Existing unsupervised domain adaptation methods aim to transfer knowledge from a label-rich source domain to an unlabeled target domain. However, obtaining labels for some source domains may be very expensive, making complete labeling as used in prior work impractical. In this work, we investigate a new domain adaptation scenario with sparsely labeled source data, where only a few examples in the source domain have been labeled, while the target domain is unlabeled. We show that when labeled source examples are limited, existing methods often fail to learn discriminative features applicable for both source and target domains. We propose a novel Cross-Domain Self-supervised (CDS) learning approach for domain adaptation, which learns features that are not only domain-invariant but also class-discriminative. Our self-supervised learning method captures apparent visual similarity with in-domain self-supervision in a domain adaptive manner and performs cross-domain feature matching with across-domain self-supervision. In extensive experiments with three standard benchmark datasets, our method significantly boosts performance of target accuracy in the new target domain with few source labels and is even helpful on classical domain adaptation scenarios.