DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation

TL;DR

DeepJDOT introduces a novel deep joint distribution optimal transport method that aligns source and target domain representations while preserving discriminative features, improving unsupervised domain adaptation in computer vision.

Contribution

It proposes a new approach combining optimal transport with deep representations to enhance unsupervised domain adaptation performance.

Findings

Outperforms state-of-the-art methods on visual recognition tasks.

Effectively aligns joint distributions of data and labels across domains.

Preserves discriminative information during domain adaptation.

Abstract

In computer vision, one is often confronted with problems of domain shifts, which occur when one applies a classifier trained on a source dataset to target data sharing similar characteristics (e.g. same classes), but also different latent data structures (e.g. different acquisition conditions). In such a situation, the model will perform poorly on the new data, since the classifier is specialized to recognize visual cues specific to the source domain. In this work we explore a solution, named DeepJDOT, to tackle this problem: through a measure of discrepancy on joint deep representations/labels based on optimal transport, we not only learn new data representations aligned between the source and target domain, but also simultaneously preserve the discriminative information used by the classifier. We applied DeepJDOT to a series of visual recognition tasks, where it compares favorably against state-of-the-art deep domain adaptation methods.