# Adversarial Alignment of Class Prediction Uncertainties for Domain Adaptation

arXiv: https://arxiv.org/abs/1804.04448 · HTML: https://mlsanity.com/paper/1804.04448/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Apr 2018.

## Built on by (most cited first, 8 of 8)

- [Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Tests](https://mlsanity.com/paper/2106.00545/) (2021)
- [RLSbench: Domain Adaptation Under Relaxed Label Shift](https://mlsanity.com/paper/2302.03020/) (2023)
- [Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection](https://mlsanity.com/paper/2110.00249/) (2021)
- [Domain Adaptive Object Detection via Balancing Between Self-Training and Adversarial Learning](https://mlsanity.com/paper/2311.04815/) (2023)
- [Learning Transferable Conceptual Prototypes for Interpretable Unsupervised Domain Adaptation](https://mlsanity.com/paper/2310.08071/) (2023)
- [Adapting Vehicle Detector to Target Domain by Adversarial Prediction Alignment](https://mlsanity.com/paper/2107.02411/) (2021)
- [UBR2S: Uncertainty-Based Resampling and Reweighting Strategy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2110.11739/) (2021)
- [ReFuSeg: Regularized Multi-Modal Fusion for Precise Brain Tumour Segmentation](https://mlsanity.com/paper/2308.13883/) (2023)

## Abstract (arXiv)

We consider unsupervised domain adaptation: given labelled examples from a source domain and unlabelled examples from a related target domain, the goal is to infer the labels of target examples. Under the assumption that features from pre-trained deep neural networks are transferable across related domains, domain adaptation reduces to aligning source and target domain at class prediction uncertainty level. We tackle this problem by introducing a method based on adversarial learning which forces the label uncertainty predictions on the target domain to be indistinguishable from those on the source domain. Pre-trained deep neural networks are used to generate deep features having high transferability across related domains. We perform an extensive experimental analysis of the proposed method over a wide set of publicly available pre-trained deep neural networks. Results of our experiments on domain adaptation tasks for image classification show that class prediction uncertainty alignment with features extracted from pre-trained deep neural networks provides an efficient, robust and effective method for domain adaptation.