# Domain Gap Estimation for Source Free Unsupervised Domain Adaptation with Many Classifiers

arXiv: https://arxiv.org/abs/2207.05785 · HTML: https://mlsanity.com/paper/2207.05785/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 12 Jul 2022.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Unsupervised Domain Adaptation with Residual Transfer Networks](https://mlsanity.com/paper/1602.04433/) (2016)
- [Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks](https://mlsanity.com/paper/1612.05424/) (2016)
- [Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1903.04064/) (2019)
- [Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering](https://mlsanity.com/paper/2003.08607/) (2020)
- [Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation](https://mlsanity.com/paper/2106.15326/) (2021)
- [Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks](https://mlsanity.com/paper/1511.06390/) (2015)
- [Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice](https://mlsanity.com/paper/2002.08681/) (2020)
- [Bi-Classifier Determinacy Maximization for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2012.06995/) (2020)
- [Cycle-consistent Conditional Adversarial Transfer Networks](https://mlsanity.com/paper/1909.07618/) (2019)
- [Light-weight Calibrator: a Separable Component for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1911.12796/) (2019)

## Built on by (most cited first, 3 of 3)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [A Comprehensive Survey on Source-free Domain Adaptation](https://mlsanity.com/paper/2302.11803/) (2023)
- [Adversarial Alignment for Source Free Object Detection](https://mlsanity.com/paper/2301.04265/) (2023)

## Abstract (arXiv)

In theory, the success of unsupervised domain adaptation (UDA) largely relies on domain gap estimation. However, for source free UDA, the source domain data can not be accessed during adaptation, which poses great challenge of measuring the domain gap. In this paper, we propose to use many classifiers to learn the source domain decision boundaries, which provides a tighter upper bound of the domain gap, even if both of the domain data can not be simultaneously accessed. The source model is trained to push away each pair of classifiers whilst ensuring the correctness of the decision boundaries. In this sense, our many classifiers model separates the source different categories as far as possible which induces the maximum disagreement of many classifiers in the target domain, thus the transferable source domain knowledge is maximized. For adaptation, the source model is adapted to maximize the agreement among pairs of the classifiers. Thus the target features are pushed away from the decision boundaries. Experiments on several datasets of UDA show that our approach achieves state of the art performance among source free UDA approaches and can even compete to source available UDA methods.