Discriminative Radial Domain Adaptation

01/01/2023
by   Zenan Huang, et al.
0

Domain adaptation methods reduce domain shift typically by learning domain-invariant features. Most existing methods are built on distribution matching, e.g., adversarial domain adaptation, which tends to corrupt feature discriminability. In this paper, we propose Discriminative Radial Domain Adaptation (DRDR) which bridges source and target domains via a shared radial structure. It's motivated by the observation that as the model is trained to be progressively discriminative, features of different categories expand outwards in different directions, forming a radial structure. We show that transferring such an inherently discriminative structure would enable to enhance feature transferability and discriminability simultaneously. Specifically, we represent each domain with a global anchor and each category a local anchor to form a radial structure and reduce domain shift via structure matching. It consists of two parts, namely isometric transformation to align the structure globally and local refinement to match each category. To enhance the discriminability of the structure, we further encourage samples to cluster close to the corresponding local anchors based on optimal-transport assignment. Extensively experimenting on multiple benchmarks, our method is shown to consistently outperforms state-of-the-art approaches on varied tasks, including the typical unsupervised domain adaptation, multi-source domain adaptation, domain-agnostic learning, and domain generalization.

READ FULL TEXT

page 1

page 10

page 13

research
10/29/2019

Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation

Unsupervised domain adaptation (UDA) aims to enhance the generalization ...
research
11/07/2020

Interventional Domain Adaptation

Domain adaptation (DA) aims to transfer discriminative features learned ...
research
08/27/2020

Adversarial Dual Distinct Classifiers for Unsupervised Domain Adaptation

Unsupervised Domain adaptation (UDA) attempts to recognize the unlabeled...
research
08/14/2021

Towards Category and Domain Alignment: Category-Invariant Feature Enhancement for Adversarial Domain Adaptation

Adversarial domain adaptation has made impressive advances in transferri...
research
07/08/2022

Unsupervised Domain Adaptive Fundus Image Segmentation with Category-level Regularization

Existing unsupervised domain adaptation methods based on adversarial lea...
research
05/28/2020

Disentanglement Then Reconstruction: Learning Compact Features for Unsupervised Domain Adaptation

Recent works in domain adaptation always learn domain invariant features...
research
12/09/2021

Domain Adaptation and Autoencoder Based Unsupervised Speech Enhancement

As a category of transfer learning, domain adaptation plays an important...

Please sign up or login with your details

Forgot password? Click here to reset