# Balancing Discriminability and Transferability for Source-Free Domain Adaptation

arXiv: https://arxiv.org/abs/2206.08009 · HTML: https://mlsanity.com/paper/2206.08009/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- Builds on 70 of its 98 references that are in the map.
- First posted on arXiv 16 Jun 2022.

## Builds on (most cited first, 30 of 70)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [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)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (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)
- [Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks](https://mlsanity.com/paper/1602.07868/) (2016)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2101.10979/) (2021)
- [Universal Source-Free Domain Adaptation](https://mlsanity.com/paper/2004.04393/) (2020)
- [Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis](https://mlsanity.com/paper/1701.02096/) (2017)
- [Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation](https://mlsanity.com/paper/2110.04202/) (2021)
- [Generalized Source-free Domain Adaptation](https://mlsanity.com/paper/2108.01614/) (2021)
- [Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer](https://mlsanity.com/paper/2012.07297/) (2020)
- [Image to Image Translation for Domain Adaptation](https://mlsanity.com/paper/1712.00479/) (2017)
- [Source-Free Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2103.16372/) (2021)
- [Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data](https://mlsanity.com/paper/2110.03374/) (2021)
- [Remix: Rebalanced Mixup](https://mlsanity.com/paper/2007.03943/) (2020)

## Built on by (most cited first, 30 of 58)

- [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)
- [On Pitfalls of Test-Time Adaptation](https://mlsanity.com/paper/2306.03536/) (2023)
- [Source-Free Domain Adaptation with Frozen Multimodal Foundation Model](https://mlsanity.com/paper/2311.16510/) (2023)
- [Source-free Depth for Object Pop-out](https://mlsanity.com/paper/2212.05370/) (2022)
- [Feature Alignment and Uniformity for Test Time Adaptation](https://mlsanity.com/paper/2303.10902/) (2023)
- [Adversarial Alignment for Source Free Object Detection](https://mlsanity.com/paper/2301.04265/) (2023)
- [TEA: Test-time Energy Adaptation](https://mlsanity.com/paper/2311.14402/) (2023)
- [SPA: A Graph Spectral Alignment Perspective for Domain Adaptation](https://mlsanity.com/paper/2310.17594/) (2023)
- [Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation](https://mlsanity.com/paper/2207.13247/) (2022)
- [Proxy Denoising for Source-Free Domain Adaptation](https://mlsanity.com/paper/2406.01658/) (2024)
- [Multi-Modal Continual Test-Time Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2303.10457/) (2023)
- [SF(DA)2: Source-free Domain Adaptation Through the Lens of Data Augmentation](https://mlsanity.com/paper/2403.10834/) (2024)
- [Subsidiary Prototype Alignment for Universal Domain Adaptation](https://mlsanity.com/paper/2210.15909/) (2022)
- [Domain-Specificity Inducing Transformers for Source-Free Domain Adaptation](https://mlsanity.com/paper/2308.14023/) (2023)
- [Source-Free Domain Adaptation with Temporal Imputation for Time Series Data](https://mlsanity.com/paper/2307.07542/) (2023)
- [Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-Training](https://mlsanity.com/paper/2405.02954/) (2024)
- [A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data](https://mlsanity.com/paper/2407.02112/) (2024)
- [Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation](https://mlsanity.com/paper/2212.07585/) (2022)
- [Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streams](https://mlsanity.com/paper/2407.12128/) (2024)
- [Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation](https://mlsanity.com/paper/2303.14361/) (2023)
- [Cal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration Error](https://mlsanity.com/paper/2308.03003/) (2023)
- [Leveraging Endo- and Exo-Temporal Regularization for Black-box Video Domain Adaptation](https://mlsanity.com/paper/2208.05187/) (2022)
- [Augmenting and Aligning Snippets for Few-Shot Video Domain Adaptation](https://mlsanity.com/paper/2303.10451/) (2023)
- [Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data](https://mlsanity.com/paper/2311.01420/) (2023)
- [Agile Multi-Source-Free Domain Adaptation](https://mlsanity.com/paper/2403.05062/) (2024)
- [Evidentially Calibrated Source-Free Time-Series Domain Adaptation with Temporal Imputation](https://mlsanity.com/paper/2406.02635/) (2024)
- [Aligning Non-Causal Factors for Transformer-Based Source-Free Domain Adaptation](https://mlsanity.com/paper/2311.16294/) (2023)
- [De-Confusing Pseudo-Labels in Source-Free Domain Adaptation](https://mlsanity.com/paper/2401.01650/) (2024)

## Abstract (arXiv)

Conventional domain adaptation (DA) techniques aim to improve domain transferability by learning domain-invariant representations; while concurrently preserving the task-discriminability knowledge gathered from the labeled source data. However, the requirement of simultaneous access to labeled source and unlabeled target renders them unsuitable for the challenging source-free DA setting. The trivial solution of realizing an effective original to generic domain mapping improves transferability but degrades task discriminability. Upon analyzing the hurdles from both theoretical and empirical standpoints, we derive novel insights to show that a mixup between original and corresponding translated generic samples enhances the discriminability-transferability trade-off while duly respecting the privacy-oriented source-free setting. A simple but effective realization of the proposed insights on top of the existing source-free DA approaches yields state-of-the-art performance with faster convergence. Beyond single-source, we also outperform multi-source prior-arts across both classification and semantic segmentation benchmarks.