mlsanityData to 14 Oct 2026

Co-Teaching for Unsupervised Domain Adaptation and Expansion

arXiv 2204.01210 ↗First posted 4 Apr 2022cs.CVcited by 0

Not on the map. Why?

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.

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

29 of 42 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  4. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  5. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  6. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  7. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  8. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  9. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  10. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  11. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  12. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 600
17 more
  1. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  2. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 541
  3. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  4. 2019Adversarial Domain Adaptation with Domain Mixupcited by 250
  5. 2021Generalized Source-free Domain Adaptationcited by 175
  6. 2020Unsupervised Domain Adaptation via Structurally Regularized Deep Clusteringcited by 140
  7. 2021CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptationcited by 129
  8. 2018Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attackcited by 125
  9. 2020FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptationcited by 124
  10. 2018DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptationcited by 101
  11. 2016Robustness of classifiers: from adversarial to random noisecited by 88
  12. 2019Transfer Learning with Dynamic Adversarial Adaptation Networkcited by 37
  13. 2021Curriculum Graph Co-Teaching for Multi-Target Domain Adaptationcited by 37
  14. 2019Improving Robustness of Deep Learning Based Knee MRI Segmentation: Mixup and Adversarial Domain Adaptationcited by 27
  15. 2021Pareto Domain Adaptationcited by 20
  16. 2021Domain Consistency Regularization for Unsupervised Multi-source Domain Adaptive Classificationcited by 6
  17. 2021Unsupervised Domain Expansion for Visual Categorizationcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Collaborative Learning for Enhanced Unsupervised Domain Adaptation
  2. 2024Unsupervised Domain Adaption Harnessing Vision-Language Pre-training
  3. 2021Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning
  4. 2022Unsupervised Domain Adaptation for Segmentation with Black-box Source Model
  5. 2023Unsupervised Domain Adaptation via Domain-Adaptive Diffusion
  6. 2026Revisiting Diffusion Fine-Tuning for Unsupervised Domain Adaptation
  7. 2025Co-STAR: Collaborative Curriculum Self-Training with Adaptive Regularization for Source-Free Video Domain Adaptation
  8. 2024Multi-Target Unsupervised Domain Adaptation for Semantic Segmentation without External Data