# Adversarial Dropout Regularization

arXiv: https://arxiv.org/abs/1711.01575 · HTML: https://mlsanity.com/paper/1711.01575/

## Key facts

- Cited by 106 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2017.

## Built on by (most cited first, 30 of 106)

- [Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation](https://mlsanity.com/paper/2110.04202/) (2021)
- [Generalized Source-free Domain Adaptation](https://mlsanity.com/paper/2108.01614/) (2021)
- [FSDR: Frequency Space Domain Randomization for Domain Generalization](https://mlsanity.com/paper/2103.02370/) (2021)
- [Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data](https://mlsanity.com/paper/2110.03374/) (2021)
- [CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2109.06165/) (2021)
- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [Unsupervised Domain Adaptation of Object Detectors: A Survey](https://mlsanity.com/paper/2105.13502/) (2021)
- [A Closer Look at Smoothness in Domain Adversarial Training](https://mlsanity.com/paper/2206.08213/) (2022)
- [Cross-domain Contrastive Learning for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2106.05528/) (2021)
- [Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2106.04151/) (2021)
- [Category Contrast for Unsupervised Domain Adaptation in Visual Tasks](https://mlsanity.com/paper/2106.02885/) (2021)
- [CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2107.00085/) (2021)
- [RDA: Robust Domain Adaptation via Fourier Adversarial Attacking](https://mlsanity.com/paper/2106.02874/) (2021)
- [Self-Supervised Noisy Label Learning for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2102.11614/) (2021)
- [When Source-Free Domain Adaptation Meets Learning with Noisy Labels](https://mlsanity.com/paper/2301.13381/) (2023)
- [Uncertainty-guided Source-free Domain Adaptation](https://mlsanity.com/paper/2208.07591/) (2022)
- [Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate](https://mlsanity.com/paper/2107.13469/) (2021)
- [Semantic Concentration for Domain Adaptation](https://mlsanity.com/paper/2108.05720/) (2021)
- [Cross-View Regularization for Domain Adaptive Panoptic Segmentation](https://mlsanity.com/paper/2103.02584/) (2021)
- [Spectral Unsupervised Domain Adaptation for Visual Recognition](https://mlsanity.com/paper/2106.06112/) (2021)
- [Multi-Objective Meta Learning](https://mlsanity.com/paper/2102.07121/) (2021)
- [PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalization](https://mlsanity.com/paper/2212.00979/) (2022)
- [ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation](https://mlsanity.com/paper/2205.14566/) (2022)
- [Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation](https://mlsanity.com/paper/2103.04705/) (2021)
- [Geometric Unsupervised Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2103.16694/) (2021)
- [ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2106.10812/) (2021)
- [ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2104.09136/) (2021)
- [Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Clouds](https://mlsanity.com/paper/2108.09169/) (2021)
- [Cross-Domain Graph Anomaly Detection via Anomaly-aware Contrastive Alignment](https://mlsanity.com/paper/2212.01096/) (2022)
- [Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning](https://mlsanity.com/paper/2104.11056/) (2021)

## Abstract (arXiv)

We present a method for transferring neural representations from label-rich source domains to unlabeled target domains. Recent adversarial methods proposed for this task learn to align features across domains by fooling a special domain critic network. However, a drawback of this approach is that the critic simply labels the generated features as in-domain or not, without considering the boundaries between classes. This can lead to ambiguous features being generated near class boundaries, reducing target classification accuracy. We propose a novel approach, Adversarial Dropout Regularization (ADR), to encourage the generator to output more discriminative features for the target domain. Our key idea is to replace the critic with one that detects non-discriminative features, using dropout on the classifier network. The generator then learns to avoid these areas of the feature space and thus creates better features. We apply our ADR approach to the problem of unsupervised domain adaptation for image classification and semantic segmentation tasks, and demonstrate significant improvement over the state of the art. We also show that our approach can be used to train Generative Adversarial Networks for semi-supervised learning.