# Visualizing Adapted Knowledge in Domain Transfer

arXiv: https://arxiv.org/abs/2104.10602 · HTML: https://mlsanity.com/paper/2104.10602/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 49 references that are in the map.
- First posted on arXiv 20 Apr 2021.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [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)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [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)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](https://mlsanity.com/paper/1912.08795/) (2019)
- [Domain Separation Networks](https://mlsanity.com/paper/1608.06019/) (2016)
- [Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks](https://mlsanity.com/paper/1612.05424/) (2016)
- [Learning from Simulated and Unsupervised Images through Adversarial Training](https://mlsanity.com/paper/1612.07828/) (2016)
- [Universal Source-Free Domain Adaptation](https://mlsanity.com/paper/2004.04393/) (2020)
- [Coupled Generative Adversarial Networks](https://mlsanity.com/paper/1606.07536/) (2016)
- [Data-Free Learning of Student Networks](https://mlsanity.com/paper/1904.01186/) (2019)
- [Generate To Adapt: Aligning Domains using Generative Adversarial Networks](https://mlsanity.com/paper/1704.01705/) (2017)
- [Deep Photo Style Transfer](https://mlsanity.com/paper/1703.07511/) (2017)

## Built on by (most cited first, 30 of 32)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [Confidence Score for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2206.06640/) (2022)
- [Source-Free Open Compound Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2106.03422/) (2021)
- [Cross-Domain Correlation Distillation for Unsupervised Domain Adaptation in Nighttime Semantic Segmentation](https://mlsanity.com/paper/2205.00858/) (2022)
- [Generative Domain Adaptation for Face Anti-Spoofing](https://mlsanity.com/paper/2207.10015/) (2022)
- [The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation](https://mlsanity.com/paper/2308.09139/) (2023)
- [Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding](https://mlsanity.com/paper/2503.16707/) (2025)
- [RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation](https://mlsanity.com/paper/2208.10531/) (2022)
- [Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling](https://mlsanity.com/paper/2206.01319/) (2022)
- [Personalized Feature Translation for Expression Recognition: An Efficient Source-Free Domain Adaptation Method](https://mlsanity.com/paper/2508.09202/) (2025)
- [Commonality in Natural Images Rescues GANs: Pretraining GANs with Generic and Privacy-free Synthetic Data](https://mlsanity.com/paper/2204.04950/) (2022)
- [Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition](https://mlsanity.com/paper/2210.05246/) (2022)
- [Reliable Source Approximation: Source-Free Unsupervised Domain Adaptation for Vestibular Schwannoma MRI Segmentation](https://mlsanity.com/paper/2405.16102/) (2024)
- [Learning Transferable Conceptual Prototypes for Interpretable Unsupervised Domain Adaptation](https://mlsanity.com/paper/2310.08071/) (2023)
- [TiGDistill-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning Distillation](https://mlsanity.com/paper/2412.20911/) (2024)
- [AdaptGuard: Defending Against Universal Attacks for Model Adaptation](https://mlsanity.com/paper/2303.10594/) (2023)
- [Target-agnostic Source-free Domain Adaptation for Regression Tasks](https://mlsanity.com/paper/2312.00540/) (2023)
- [Explaining Cross-Domain Recognition with Interpretable Deep Classifier](https://mlsanity.com/paper/2211.08249/) (2022)
- [Dual Moving Average Pseudo-Labeling for Source-Free Inductive Domain Adaptation](https://mlsanity.com/paper/2212.08187/) (2022)
- [Contrast and Clustering: Learning Neighborhood Pair Representation for Source-free Domain Adaptation](https://mlsanity.com/paper/2301.13428/) (2023)
- [Explainable Supervised Domain Adaptation](https://mlsanity.com/paper/2205.09943/) (2022)
- [Learning to Structure an Image with Few Colors and Beyond](https://mlsanity.com/paper/2208.08438/) (2022)
- [Rectifying Group Irregularities in Explanations for Distribution Shift](https://mlsanity.com/paper/2305.16308/) (2023)
- [Trustworthy Representation Learning Across Domains](https://mlsanity.com/paper/2308.12315/) (2023)
- [An Investigation of Test-time Adaptation for Audio Classification under Background Noise](https://mlsanity.com/paper/2507.15523/) (2025)
- [PhysFire-WM: A Physics-Informed World Model for Emulating Fire Spread Dynamics](https://mlsanity.com/paper/2512.17152/) (2025)
- [High-order Neighborhoods Know More: HyperGraph Learning Meets Source-free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2405.06916/) (2024)
- [A3: Active Adversarial Alignment for Source-Free Domain Adaptation](https://mlsanity.com/paper/2409.18418/) (2024)
- [AdaptiveCDM: Source-Free Few-Shot Domain Adaptation for Cell Detection in Microscopic Images](https://mlsanity.com/paper/2503.03370/) (2025)

## Abstract (arXiv)

A source model trained on source data and a target model learned through unsupervised domain adaptation (UDA) usually encode different knowledge. To understand the adaptation process, we portray their knowledge difference with image translation. Specifically, we feed a translated image and its original version to the two models respectively, formulating two branches. Through updating the translated image, we force similar outputs from the two branches. When such requirements are met, differences between the two images can compensate for and hence represent the knowledge difference between models. To enforce similar outputs from the two branches and depict the adapted knowledge, we propose a source-free image translation method that generates source-style images using only target images and the two models. We visualize the adapted knowledge on several datasets with different UDA methods and find that generated images successfully capture the style difference between the two domains. For application, we show that generated images enable further tuning of the target model without accessing source data. Code available at https://github.com/hou-yz/DA_visualization.