# Transferrable Prototypical Networks for Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/1904.11227 · HTML: https://mlsanity.com/paper/1904.11227/

## Key facts

- Cited by 141 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Apr 2019.

## Built on by (most cited first, 30 of 141)

- [MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation](https://mlsanity.com/paper/2212.01322/) (2022)
- [Domain Adaptation via Prompt Learning](https://mlsanity.com/paper/2202.06687/) (2022)
- [PMR: Prototypical Modal Rebalance for Multimodal Learning](https://mlsanity.com/paper/2211.07089/) (2022)
- [Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation](https://mlsanity.com/paper/2106.15326/) (2021)
- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [Personalized Federated Learning with Feature Alignment and Classifier Collaboration](https://mlsanity.com/paper/2306.11867/) (2023)
- [VDM-DA: Virtual Domain Modeling for Source Data-free Domain Adaptation](https://mlsanity.com/paper/2103.14357/) (2021)
- [A Prototype-Oriented Framework for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2110.12024/) (2021)
- [Transferable Semantic Augmentation for Domain Adaptation](https://mlsanity.com/paper/2103.12562/) (2021)
- [Dynamic Weighted Learning for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2103.13814/) (2021)
- [Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate](https://mlsanity.com/paper/2107.13469/) (2021)
- [Your Classifier can Secretly Suffice Multi-Source Domain Adaptation](https://mlsanity.com/paper/2103.11169/) (2021)
- [Hyperbolic Busemann Learning with Ideal Prototypes](https://mlsanity.com/paper/2106.14472/) (2021)
- [Generalized Category Discovery with Decoupled Prototypical Network](https://mlsanity.com/paper/2211.15115/) (2022)
- [Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation](https://mlsanity.com/paper/2207.10856/) (2022)
- [A Style and Semantic Memory Mechanism for Domain Generalization](https://mlsanity.com/paper/2112.07517/) (2021)
- [ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2104.09136/) (2021)
- [Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Clouds](https://mlsanity.com/paper/2108.09169/) (2021)
- [Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2209.07695/) (2022)
- [Upcycling Models under Domain and Category Shift](https://mlsanity.com/paper/2303.07110/) (2023)
- [POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained models](https://mlsanity.com/paper/2305.00350/) (2023)
- [I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors](https://mlsanity.com/paper/2103.13757/) (2021)
- [Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation](https://mlsanity.com/paper/2109.04015/) (2021)
- [Confidence Calibration for Domain Generalization under Covariate Shift](https://mlsanity.com/paper/2104.00742/) (2021)
- [Meta-learning approaches for few-shot learning: A survey of recent advances](https://mlsanity.com/paper/2303.07502/) (2023)
- [Leveraging Self-Supervision for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2103.16291/) (2021)
- [T-SVDNet: Exploring High-Order Prototypical Correlations for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2107.14447/) (2021)
- [Prototype Guided Federated Learning of Visual Feature Representations](https://mlsanity.com/paper/2105.08982/) (2021)
- [Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2104.01286/) (2021)
- [Pareto Domain Adaptation](https://mlsanity.com/paper/2112.04137/) (2021)

## Abstract (arXiv)

In this paper, we introduce a new idea for unsupervised domain adaptation via a remold of Prototypical Networks, which learn an embedding space and perform classification via a remold of the distances to the prototype of each class. Specifically, we present Transferrable Prototypical Networks (TPN) for adaptation such that the prototypes for each class in source and target domains are close in the embedding space and the score distributions predicted by prototypes separately on source and target data are similar. Technically, TPN initially matches each target example to the nearest prototype in the source domain and assigns an example a "pseudo" label. The prototype of each class could then be computed on source-only, target-only and source-target data, respectively. The optimization of TPN is end-to-end trained by jointly minimizing the distance across the prototypes on three types of data and KL-divergence of score distributions output by each pair of the prototypes. Extensive experiments are conducted on the transfers across MNIST, USPS and SVHN datasets, and superior results are reported when comparing to state-of-the-art approaches. More remarkably, we obtain an accuracy of 80.4% of single model on VisDA 2017 dataset.