# SWAT: Sliding Window Adversarial Training for Gradual Domain Adaptation

arXiv: https://arxiv.org/abs/2501.19155 · HTML: https://mlsanity.com/paper/2501.19155/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 52 references that are in the map.
- First posted on arXiv 31 Jan 2025.

## Builds on (most cited first, 30 of 33)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [RobustBench: a standardized adversarial robustness benchmark](https://mlsanity.com/paper/2010.09670/) (2020)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [A Brief Review of Domain Adaptation](https://mlsanity.com/paper/2010.03978/) (2020)
- [Gradient Starvation: A Learning Proclivity in Neural Networks](https://mlsanity.com/paper/2011.09468/) (2020)
- [Contrastive Test-Time Adaptation](https://mlsanity.com/paper/2204.10377/) (2022)
- [DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1803.10081/) (2018)
- [Multi-Adversarial Domain Adaptation](https://mlsanity.com/paper/1809.02176/) (2018)
- [Understanding Self-Training for Gradual Domain Adaptation](https://mlsanity.com/paper/2002.11361/) (2020)
- [A Closer Look at Smoothness in Domain Adversarial Training](https://mlsanity.com/paper/2206.08213/) (2022)
- [Discriminative Adversarial Domain Adaptation](https://mlsanity.com/paper/1911.12036/) (2019)
- [The Limitations of Adversarial Training and the Blind-Spot Attack](https://mlsanity.com/paper/1901.04684/) (2019)
- [A Century of Portraits: A Visual Historical Record of American High School Yearbooks](https://mlsanity.com/paper/1511.02575/) (2015)
- [Adversarial Domain Adaptation for Stable Brain-Machine Interfaces](https://mlsanity.com/paper/1810.00045/) (2018)
- [Gradual Domain Adaptation without Indexed Intermediate Domains](https://mlsanity.com/paper/2207.04587/) (2022)
- [SPA: A Graph Spectral Alignment Perspective for Domain Adaptation](https://mlsanity.com/paper/2310.17594/) (2023)
- [Gradual Domain Adaptation: Theory and Algorithms](https://mlsanity.com/paper/2310.13852/) (2023)

## Abstract (arXiv)

Domain shifts are critical issues that harm the performance of machine learning. Unsupervised Domain Adaptation (UDA) mitigates this issue but suffers when the domain shifts are steep and drastic. Gradual Domain Adaptation (GDA) alleviates this problem in a mild way by gradually adapting from the source to the target domain using multiple intermediate domains. In this paper, we propose Sliding Window Adversarial Training (SWAT) for GDA. SWAT first formulates adversarial streams to connect the feature spaces of the source and target domains. Then, a sliding window paradigm is designed that moves along the adversarial stream to gradually narrow the small gap between adjacent intermediate domains. When the window moves to the end of the stream, i.e., the target domain, the domain shift is explicitly reduced. Extensive experiments on six GDA benchmarks demonstrate the significant effectiveness of SWAT, especially 6.1% improvement on Rotated MNIST and 4.1% advantage on CIFAR-100C over the previous methods.