Unsupervised Domain Adaptation via Deep Hierarchical Optimal Transport

by   Yingxue Xu, et al.

Unsupervised domain adaptation is a challenging task that aims to estimate a transferable model for unlabeled target domain by exploiting source labeled data. Optimal Transport (OT) based methods recently have been proven to be a promising direction for domain adaptation due to their competitive performance. However, most of these methods coarsely aligned source and target distributions, leading to the over-aligned problem where the category-discriminative information is mixed up although domain-invariant representations can be learned. In this paper, we propose a Deep Hierarchical Optimal Transport method (DeepHOT) for unsupervised domain adaptation. The main idea is to use hierarchical optimal transport to learn both domain-invariant and category-discriminative representations by mining the rich structural correlations among domain data. The DeepHOT framework consists of a domain-level OT and an image-level OT, where the latter is used as the ground distance metric for the former. The image-level OT captures structural associations of local image regions that are beneficial to image classification, while the domain-level OT learns domain-invariant representations by leveraging the underlying geometry of domains. However, due to the high computational complexity, the optimal transport based models are limited in some scenarios. To this end, we propose a robust and efficient implementation of the DeepHOT framework by approximating origin OT with sliced Wasserstein distance in image-level OT and using a mini-batch unbalanced optimal transport for domain-level OT. Extensive experiments show that DeepHOT surpasses the state-of-the-art methods in four benchmark datasets. Code will be released on GitHub.


page 1

page 2

page 3

page 4


Hierarchical Optimal Transport for Unsupervised Domain Adaptation

In this paper, we propose a novel approach for unsupervised domain adapt...

Feature Selection for Unsupervised Domain Adaptation using Optimal Transport

In this paper, we propose a new feature selection method for unsupervise...

Metric Learning-enhanced Optimal Transport for Biochemical Regression Domain Adaptation

Generalizing knowledge beyond source domains is a crucial prerequisite f...

Multimodal Optimal Transport-based Co-Attention Transformer with Global Structure Consistency for Survival Prediction

Survival prediction is a complicated ordinal regression task that aims t...

Implicit Bayes Adaptation: A Collaborative Transport Approach

The power and flexibility of Optimal Transport (OT) have pervaded a wide...

Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation

Curriculum Reinforcement Learning (CRL) aims to create a sequence of tas...

Iterative Barycenter Flows

The task of mapping two or more distributions to a shared representation...

Please sign up or login with your details

Forgot password? Click here to reset