Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation
arXiv:1910.05562
Abstract
Recent works on domain adaptation exploit adversarial training to obtain domain-invariant feature representations from the joint learning of feature extractor and domain discriminator networks. However, domain adversarial methods render suboptimal performances since they attempt to match the distributions among the domains without considering the task at hand. We propose Drop to Adapt (DTA), which leverages adversarial dropout to learn strongly discriminative features by enforcing the cluster assumption. Accordingly, we design objective functions to support robust domain adaptation. We demonstrate efficacy of the proposed method on various experiments and achieve consistent improvements in both image classification and semantic segmentation tasks. Our source code is available at https://github.com/postBG/DTA.pytorch.
ICCV 2019
References in corpus (9)
- How transferable are features in deep neural networks?
- Learning Transferable Features with Deep Adaptation Networks
- Conditional Adversarial Domain Adaptation
- Unsupervised Domain Adaptation with Residual Transfer Networks
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- Domain Separation Networks
- VisDA: The Visual Domain Adaptation Challenge
- Adversarial Discriminative Domain Adaptation
- Virtual Worlds as Proxy for Multi-Object Tracking Analysis