# Light-weight Calibrator: a Separable Component for Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/1911.12796 · HTML: https://mlsanity.com/paper/1911.12796/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2019.

## Built on by (most cited first, 13 of 13)

- [Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models](https://mlsanity.com/paper/2203.06904/) (2022)
- [Generalized Source-free Domain Adaptation](https://mlsanity.com/paper/2108.01614/) (2021)
- [Dynamic Weighted Learning for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2103.13814/) (2021)
- [DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation](https://mlsanity.com/paper/2103.13447/) (2021)
- [Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving](https://mlsanity.com/paper/2304.11928/) (2023)
- [Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment](https://mlsanity.com/paper/2110.06448/) (2021)
- [Gradient Harmonization in Unsupervised Domain Adaptation](https://mlsanity.com/paper/2408.00288/) (2024)
- [Dynamic Instance Domain Adaptation](https://mlsanity.com/paper/2203.05028/) (2022)
- [Repaint: Improving the Generalization of Down-Stream Visual Tasks by Generating Multiple Instances of Training Examples](https://mlsanity.com/paper/2110.10366/) (2021)
- [Domain Gap Estimation for Source Free Unsupervised Domain Adaptation with Many Classifiers](https://mlsanity.com/paper/2207.05785/) (2022)
- [Exploring Generalizable Distillation for Efficient Medical Image Segmentation](https://mlsanity.com/paper/2207.12995/) (2022)
- [Decoupled Doubly Contrastive Learning for Cross Domain Facial Action Unit Detection](https://mlsanity.com/paper/2503.08977/) (2025)
- [Subspace-Configurable Networks](https://mlsanity.com/paper/2305.13536/) (2023)

## Abstract (arXiv)

Existing domain adaptation methods aim at learning features that can be generalized among domains. These methods commonly require to update source classifier to adapt to the target domain and do not properly handle the trade off between the source domain and the target domain. In this work, instead of training a classifier to adapt to the target domain, we use a separable component called data calibrator to help the fixed source classifier recover discrimination power in the target domain, while preserving the source domain's performance. When the difference between two domains is small, the source classifier's representation is sufficient to perform well in the target domain and outperforms GAN-based methods in digits. Otherwise, the proposed method can leverage synthetic images generated by GANs to boost performance and achieve state-of-the-art performance in digits datasets and driving scene semantic segmentation. Our method empirically reveals that certain intriguing hints, which can be mitigated by adversarial attack to domain discriminators, are one of the sources for performance degradation under the domain shift.