Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation

by   Lin Chen, et al.

Adversarial learning has achieved remarkable performances for unsupervised domain adaptation (UDA). Existing adversarial UDA methods typically adopt an additional discriminator to play the min-max game with a feature extractor. However, most of these methods failed to effectively leverage the predicted discriminative information, and thus cause mode collapse for generator. In this work, we address this problem from a different perspective and design a simple yet effective adversarial paradigm in the form of a discriminator-free adversarial learning network (DALN), wherein the category classifier is reused as a discriminator, which achieves explicit domain alignment and category distinguishment through a unified objective, enabling the DALN to leverage the predicted discriminative information for sufficient feature alignment. Basically, we introduce a Nuclear-norm Wasserstein discrepancy (NWD) that has definite guidance meaning for performing discrimination. Such NWD can be coupled with the classifier to serve as a discriminator satisfying the K-Lipschitz constraint without the requirements of additional weight clipping or gradient penalty strategy. Without bells and whistles, DALN compares favorably against the existing state-of-the-art (SOTA) methods on a variety of public datasets. Moreover, as a plug-and-play technique, NWD can be directly used as a generic regularizer to benefit existing UDA algorithms. Code is available at


Crucial Semantic Classifier-based Adversarial Learning for Unsupervised Domain Adaptation

Unsupervised Domain Adaptation (UDA), which aims to explore the transfer...

Discriminator-free Unsupervised Domain Adaptation for Multi-label Image Classification

In this paper, a discriminator-free adversarial-based Unsupervised Domai...

Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation

Recent works on domain adaptation exploit adversarial training to obtain...

UDBNET: Unsupervised Document Binarization Network via Adversarial Game

Degraded document image binarization is one of the most challenging task...

Gradually Vanishing Bridge for Adversarial Domain Adaptation

In unsupervised domain adaptation, rich domain-specific characteristics ...

Graph-Relational Domain Adaptation

Existing domain adaptation methods tend to treat every domain equally an...

Please sign up or login with your details

Forgot password? Click here to reset