# Co-Teaching for Unsupervised Domain Adaptation and Expansion

arXiv: https://arxiv.org/abs/2204.01210 · HTML: https://mlsanity.com/paper/2204.01210/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 42 references that are in the map.
- First posted on arXiv 4 Apr 2022.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [Adversarial Domain Adaptation with Domain Mixup](https://mlsanity.com/paper/1912.01805/) (2019)
- [Generalized Source-free Domain Adaptation](https://mlsanity.com/paper/2108.01614/) (2021)
- [Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering](https://mlsanity.com/paper/2003.08607/) (2020)
- [CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2109.06165/) (2021)
- [Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attack](https://mlsanity.com/paper/1811.09310/) (2018)
- [FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2011.09230/) (2020)
- [DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation](https://mlsanity.com/paper/1804.05827/) (2018)
- [Robustness of classifiers: from adversarial to random noise](https://mlsanity.com/paper/1608.08967/) (2016)
- [Transfer Learning with Dynamic Adversarial Adaptation Network](https://mlsanity.com/paper/1909.08184/) (2019)
- [Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation](https://mlsanity.com/paper/2104.00808/) (2021)
- [Improving Robustness of Deep Learning Based Knee MRI Segmentation: Mixup and Adversarial Domain Adaptation](https://mlsanity.com/paper/1908.04126/) (2019)
- [Pareto Domain Adaptation](https://mlsanity.com/paper/2112.04137/) (2021)
- [Domain Consistency Regularization for Unsupervised Multi-source Domain Adaptive Classification](https://mlsanity.com/paper/2106.08590/) (2021)
- [Unsupervised Domain Expansion for Visual Categorization](https://mlsanity.com/paper/2104.00233/) (2021)

## Abstract (arXiv)

Unsupervised Domain Adaptation (UDA) essentially trades a model's performance on a source domain for improving its performance on a target domain. To overcome this, Unsupervised Domain Expansion (UDE) has been introduced, which adapts the model to the target domain while preserving its performance in the source domain. In both UDA and UDE, a model tailored to a given domain is assumed to well handle samples from the given domain. We question the assumption by reporting the existence of cross-domain visual ambiguity: Due to the unclear boundary between the two domains, samples from one domain can be visually close to the other domain. Such sorts of samples are typically in the minority in their host domain, so they tend to be overlooked by the domain-specific model, but can be better handled by a model from the other domain. We exploit this finding by proposing Co-Teaching (CT), which is instantiated with knowledge distillation based CT (kdCT) plus mixup based CT (miCT). Specifically, kdCT leverages a dual-teacher architecture to enhance the student network's ability to handle cross-domain ambiguity. Meanwhile, miCT further enhances the generalization ability of the student. Extensive experiments on image classification and driving-scene segmentation show the viability of CT for UDE.