# TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation

arXiv: https://arxiv.org/abs/2106.06326 · HTML: https://mlsanity.com/paper/2106.06326/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 85 references that are in the map.
- First posted on arXiv 11 Jun 2021.

## Builds on (most cited first, 30 of 47)

- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Generalizing from a Few Examples: A Survey on Few-Shot Learning](https://mlsanity.com/paper/1904.05046/) (2019)
- [See through Gradients: Image Batch Recovery via GradInversion](https://mlsanity.com/paper/2104.07586/) (2021)
- [Meta-Transfer Learning for Few-Shot Learning](https://mlsanity.com/paper/1812.02391/) (2018)
- [Temporal Segment Networks for Action Recognition in Videos](https://mlsanity.com/paper/1705.02953/) (2017)
- [Data Augmentation Generative Adversarial Networks](https://mlsanity.com/paper/1711.04340/) (2017)
- [The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks](https://mlsanity.com/paper/1911.07135/) (2019)
- [Universal Source-Free Domain Adaptation](https://mlsanity.com/paper/2004.04393/) (2020)
- [A DIRT-T Approach to Unsupervised Domain Adaptation](https://mlsanity.com/paper/1802.08735/) (2018)
- [Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning](https://mlsanity.com/paper/1805.10002/) (2018)
- [Low-Shot Learning from Imaginary Data](https://mlsanity.com/paper/1801.05401/) (2018)
- [Free Lunch for Few-shot Learning: Distribution Calibration](https://mlsanity.com/paper/2101.06395/) (2021)
- [Learning Deep Kernels for Non-Parametric Two-Sample Tests](https://mlsanity.com/paper/2002.09116/) (2020)
- [Towards a Neural Statistician](https://mlsanity.com/paper/1606.02185/) (2016)
- [Few-Shot Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.02536/) (2017)
- [Neural Voice Cloning with a Few Samples](https://mlsanity.com/paper/1802.06006/) (2018)
- [Rethinking Importance Weighting for Deep Learning under Distribution Shift](https://mlsanity.com/paper/2006.04662/) (2020)
- [Dynamic Instance Normalization for Arbitrary Style Transfer](https://mlsanity.com/paper/1911.06953/) (2019)
- [Few-Shot Adaptive Gaze Estimation](https://mlsanity.com/paper/1905.01941/) (2019)
- [A Universal Representation Transformer Layer for Few-Shot Image Classification](https://mlsanity.com/paper/2006.11702/) (2020)
- [FocalMix: Semi-Supervised Learning for 3D Medical Image Detection](https://mlsanity.com/paper/2003.09108/) (2020)
- [What Can Be Transferred: Unsupervised Domain Adaptation for Endoscopic Lesions Segmentation](https://mlsanity.com/paper/2004.11500/) (2020)
- [Open Set Domain Adaptation: Theoretical Bound and Algorithm](https://mlsanity.com/paper/1907.08375/) (2019)
- [Few-shot Domain Adaptation by Causal Mechanism Transfer](https://mlsanity.com/paper/2002.03497/) (2020)

## Built on by (most cited first, 17 of 17)

- [Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation](https://mlsanity.com/paper/2407.19523/) (2024)
- [Boosting Offline Reinforcement Learning with Action Preference Query](https://mlsanity.com/paper/2306.03362/) (2023)
- [Bayesian-guided Label Mapping for Visual Reprogramming](https://mlsanity.com/paper/2410.24018/) (2024)
- [Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments](https://mlsanity.com/paper/2504.19139/) (2025)
- [DUAL: Learning Diverse Kernels for Aggregated Two-sample and Independence Testing](https://mlsanity.com/paper/2510.11140/) (2025)
- [Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigation](https://mlsanity.com/paper/2510.08962/) (2025)
- [Uncertainty-Guided Mixup for Semi-Supervised Domain Adaptation without Source Data](https://mlsanity.com/paper/2107.06707/) (2021)
- [Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation](https://mlsanity.com/paper/2307.05948/) (2023)
- [MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependence](https://mlsanity.com/paper/2405.18786/) (2024)
- [Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction](https://mlsanity.com/paper/2506.04650/) (2025)
- [Autonomous Cross Domain Adaptation under Extreme Label Scarcity](https://mlsanity.com/paper/2209.01548/) (2022)
- [A Framework for Supervised Heterogeneous Transfer Learning using Dynamic Distribution Adaptation and Manifold Regularization](https://mlsanity.com/paper/2108.12293/) (2021)
- [Universal Semi-supervised Model Adaptation via Collaborative Consistency Training](https://mlsanity.com/paper/2307.03449/) (2023)
- [DMSC: Dynamic Multi-Scale Coordination Framework for Time Series Forecasting](https://mlsanity.com/paper/2508.02753/) (2025)
- [Anchor-based Maximum Discrepancy for Relative Similarity Testing](https://mlsanity.com/paper/2510.10477/) (2025)
- [SpaCellAgent: A Self-Evolving LLM-Based Multi-Agent Framework for Trajectory Analysis](https://mlsanity.com/paper/2607.07467/) (2026)
- [Dual-Prototype Disentanglement: A Context-Aware Enhancement Framework for Time Series Forecasting](https://mlsanity.com/paper/2601.16632/) (2026)

## Abstract (arXiv)

In few-shot domain adaptation (FDA), classifiers for the target domain are trained with accessible labeled data in the source domain (SD) and few labeled data in the target domain (TD). However, data usually contain private information in the current era, e.g., data distributed on personal phones. Thus, the private information will be leaked if we directly access data in SD to train a target-domain classifier (required by FDA methods). In this paper, to thoroughly prevent the privacy leakage in SD, we consider a very challenging problem setting, where the classifier for the TD has to be trained using few labeled target data and a well-trained SD classifier, named few-shot hypothesis adaptation (FHA). In FHA, we cannot access data in SD, as a result, the private information in SD will be protected well. To this end, we propose a target orientated hypothesis adaptation network (TOHAN) to solve the FHA problem, where we generate highly-compatible unlabeled data (i.e., an intermediate domain) to help train a target-domain classifier. TOHAN maintains two deep networks simultaneously, where one focuses on learning an intermediate domain and the other takes care of the intermediate-to-target distributional adaptation and the target-risk minimization. Experimental results show that TOHAN outperforms competitive baselines significantly.