# Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/1910.05562 · HTML: https://mlsanity.com/paper/1910.05562/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Oct 2019.

## Built on by (most cited first, 30 of 62)

- [RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening](https://mlsanity.com/paper/2103.15597/) (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)
- [Domain Impression: A Source Data Free Domain Adaptation Method](https://mlsanity.com/paper/2102.09003/) (2021)
- [TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2108.05988/) (2021)
- [On the Stability-Plasticity Dilemma of Class-Incremental Learning](https://mlsanity.com/paper/2304.01663/) (2023)
- [Cross-View Regularization for Domain Adaptive Panoptic Segmentation](https://mlsanity.com/paper/2103.02584/) (2021)
- [Gradual Domain Adaptation without Indexed Intermediate Domains](https://mlsanity.com/paper/2207.04587/) (2022)
- [Leveraging Self-Supervision for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2103.16291/) (2021)
- [Semi-supervised Domain Adaptation via Sample-to-Sample Self-Distillation](https://mlsanity.com/paper/2111.14353/) (2021)
- [UMAD: Universal Model Adaptation under Domain and Category Shift](https://mlsanity.com/paper/2112.08553/) (2021)
- [DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2207.09988/) (2022)
- [Unsupervised Continual Semantic Adaptation through Neural Rendering](https://mlsanity.com/paper/2211.13969/) (2022)
- [SPA: A Graph Spectral Alignment Perspective for Domain Adaptation](https://mlsanity.com/paper/2310.17594/) (2023)
- [DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalization](https://mlsanity.com/paper/2308.10285/) (2023)
- [Discovering Distinctive "Semantics" in Super-Resolution Networks](https://mlsanity.com/paper/2108.00406/) (2021)
- [Pareto Domain Adaptation](https://mlsanity.com/paper/2112.04137/) (2021)
- [S3VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptation](https://mlsanity.com/paper/2109.08901/) (2021)
- [Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors](https://mlsanity.com/paper/2205.14467/) (2022)
- [Learning Semantic Segmentation from Multiple Datasets with Label Shifts](https://mlsanity.com/paper/2202.14030/) (2022)
- [Feature Alignment by Uncertainty and Self-Training for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2208.14888/) (2022)
- [Divergence Optimization for Noisy Universal Domain Adaptation](https://mlsanity.com/paper/2104.00246/) (2021)
- [Unsupervised RGB-to-Thermal Domain Adaptation via Multi-Domain Attention Network](https://mlsanity.com/paper/2210.04367/) (2022)
- [Self-training Guided Adversarial Domain Adaptation For Thermal Imagery](https://mlsanity.com/paper/2106.07165/) (2021)
- [A Curriculum-style Self-training Approach for Source-Free Semantic Segmentation](https://mlsanity.com/paper/2106.11653/) (2021)
- [Partial Domain Adaptation without Domain Alignment](https://mlsanity.com/paper/2108.12867/) (2021)
- [Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2104.02633/) (2021)
- [An Unsupervised Domain Adaptation Model based on Dual-module Adversarial Training](https://mlsanity.com/paper/2112.15555/) (2021)
- [Mining Data Impressions from Deep Models as Substitute for the Unavailable Training Data](https://mlsanity.com/paper/2101.06069/) (2021)
- [Generalizable Facial Expression Recognition](https://mlsanity.com/paper/2408.10614/) (2024)

## Abstract (arXiv)

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.