# Jacobian Norm for Unsupervised Source-Free Domain Adaptation

arXiv: https://arxiv.org/abs/2204.03467 · HTML: https://mlsanity.com/paper/2204.03467/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 48 references that are in the map.
- First posted on arXiv 7 Apr 2022.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (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)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [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)
- [Deep Transfer Learning with Joint Adaptation Networks](https://mlsanity.com/paper/1605.06636/) (2016)
- [Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning](https://mlsanity.com/paper/1702.08811/) (2017)
- [Generate To Adapt: Aligning Domains using Generative Adversarial Networks](https://mlsanity.com/paper/1704.01705/) (2017)
- [Progressive Feature Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1811.08585/) (2018)
- [A review of domain adaptation without target labels](https://mlsanity.com/paper/1901.05335/) (2019)
- [Domain Agnostic Learning with Disentangled Representations](https://mlsanity.com/paper/1904.12347/) (2019)
- [Improved OOD Generalization via Adversarial Training and Pre-training](https://mlsanity.com/paper/2105.11144/) (2021)
- [Multi-Source Domain Adaptation for Text Classification via DistanceNet-Bandits](https://mlsanity.com/paper/2001.04362/) (2020)
- [Adversarial Bipartite Graph Learning for Video Domain Adaptation](https://mlsanity.com/paper/2007.15829/) (2020)
- [Dual Path Learning for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/2108.06337/) (2021)
- [Source-free Domain Adaptation via Distributional Alignment by Matching Batch Normalization Statistics](https://mlsanity.com/paper/2101.10842/) (2021)
- [Casting a BAIT for Offline and Online Source-free Domain Adaptation](https://mlsanity.com/paper/2010.12427/) (2020)
- [Beyond H-Divergence: Domain Adaptation Theory With Jensen-Shannon Divergence](https://mlsanity.com/paper/2007.15567/) (2020)
- [Heterogeneous Domain Adaptation via Soft Transfer Network](https://mlsanity.com/paper/1908.10552/) (2019)
- [Transferrable Contrastive Learning for Visual Domain Adaptation](https://mlsanity.com/paper/2112.07516/) (2021)
- [Adaptively-Accumulated Knowledge Transfer for Partial Domain Adaptation](https://mlsanity.com/paper/2008.11873/) (2020)
- [Guaranteed Deterministic Bounds on the Total Variation Distance between Univariate Mixtures](https://mlsanity.com/paper/1806.11311/) (2018)
- [Unsupervised Domain Adaptation with Progressive Adaptation of Subspaces](https://mlsanity.com/paper/2009.00520/) (2020)
- [On the inductive biases of deep domain adaptation](https://mlsanity.com/paper/2109.07920/) (2021)

## Built on by (most cited first, 4 of 4)

- [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)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [High-order Neighborhoods Know More: HyperGraph Learning Meets Source-free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2405.06916/) (2024)

## Abstract (arXiv)

Unsupervised Source (data) Free domain adaptation (USFDA) aims to transfer knowledge from a well-trained source model to a related but unlabeled target domain. In such a scenario, all conventional adaptation methods that require source data fail. To combat this challenge, existing USFDAs turn to transfer knowledge by aligning the target feature to the latent distribution hidden in the source model. However, such information is naturally limited. Thus, the alignment in such a scenario is not only difficult but also insufficient, which degrades the target generalization performance. To relieve this dilemma in current USFDAs, we are motivated to explore a new perspective to boost their performance. For this purpose and gaining necessary insight, we look back upon the origin of the domain adaptation and first theoretically derive a new-brand target generalization error bound based on the model smoothness. Then, following the theoretical insight, a general and model-smoothness-guided Jacobian norm (JN) regularizer is designed and imposed on the target domain to mitigate this dilemma. Extensive experiments are conducted to validate its effectiveness. In its implementation, just with a few lines of codes added to the existing USFDAs, we achieve superior results on various benchmark datasets.