Learning a Domain-Invariant Embedding for Unsupervised Domain Adaptation Using Class-Conditioned Distribution Alignment

by   Alex Gabourie, et al.

We address the problem of unsupervised domain adaptation (UDA) by learning a cross-domain agnostic embedding space, where the distance between the probability distributions of the two source and target visual domains is minimized. We use the output space of a shared cross-domain deep encoder to model the embedding space anduse the Sliced-Wasserstein Distance (SWD) to measure and minimize the distance between the embedded distributions of two source and target domains to enforce the embedding to be domain-agnostic.Additionally, we use the source domain labeled data to train a deep classifier from the embedding space to the label space to enforce the embedding space to be discriminative.As a result of this training scheme, we provide an effective solution to train the deep classification network on the source domain such that it will generalize well on the target domain, where only unlabeled training data is accessible. To mitigate the challenge of class matching, we also align corresponding classes in the embedding space by using high confidence pseudo-labels for the target domain, i.e. assigning the class for which the source classifier has a high prediction probability. We provide theoretical justification as well as experimental results on UDA benchmark tasks to demonstrate that our method is effective and leads to state-of-the-art performance.


page 3

page 6


Increasing Model Generalizability for Unsupervised Domain Adaptation

A dominant approach for addressing unsupervised domain adaptation is to ...

Unsupervised Domain Adaptation for Graph-Structured Data Using Class-Conditional Distribution Alignment

Adopting deep learning models for graph-structured data is challenging d...

Domain Adaptation for Sentiment Analysis Using Increased Intraclass Separation

Sentiment analysis is a costly yet necessary task for enterprises to stu...

Transferrable Prototypical Networks for Unsupervised Domain Adaptation

In this paper, we introduce a new idea for unsupervised domain adaptatio...

Unsupervised Cross-domain Image Classification by Distance Metric Guided Feature Alignment

Learning deep neural networks that are generalizable across different do...

Associative Domain Adaptation

We propose associative domain adaptation, a novel technique for end-to-e...

Towards Robust Cross-domain Image Understanding with Unsupervised Noise Removal

Deep learning models usually require a large amount of labeled data to a...

Please sign up or login with your details

Forgot password? Click here to reset