# Deep Transfer Network: Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/1503.00591 · HTML: https://mlsanity.com/paper/1503.00591/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2015.

## Built on by (most cited first, 20 of 20)

- [Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation](https://mlsanity.com/paper/2104.00808/) (2021)
- [A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions](https://mlsanity.com/paper/2307.05638/) (2023)
- [Learning Domain-Aware Detection Head with Prompt Tuning](https://mlsanity.com/paper/2306.05718/) (2023)
- [Benchmarking Test-Time Adaptation against Distribution Shifts in Image Classification](https://mlsanity.com/paper/2307.03133/) (2023)
- [Multi-Source domain adaptation via supervised contrastive learning and confident consistency regularization](https://mlsanity.com/paper/2106.16093/) (2021)
- [Decomposition-based Unsupervised Domain Adaptation for Remote Sensing Image Semantic Segmentation](https://mlsanity.com/paper/2404.04531/) (2024)
- [Source-free Unsupervised Domain Adaptation for Blind Image Quality Assessment](https://mlsanity.com/paper/2207.08124/) (2022)
- [From Canteen Food to Daily Meals: Generalizing Food Recognition to More Practical Scenarios](https://mlsanity.com/paper/2403.07403/) (2024)
- [DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection](https://mlsanity.com/paper/2410.09004/) (2024)
- [Analytic Continual Test-Time Adaptation for Multi-Modality Corruption](https://mlsanity.com/paper/2410.22373/) (2024)
- [PIG: Prompt Images Guidance for Night-Time Scene Parsing](https://mlsanity.com/paper/2406.10531/) (2024)
- [Class-Aware Universum Inspired Re-Balance Learning for Long-Tailed Recognition](https://mlsanity.com/paper/2207.12808/) (2022)
- [Modeling Hierarchical Structural Distance for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2211.11424/) (2022)
- [Iterative self-transfer learning: A general methodology for response time-history prediction based on small dataset](https://mlsanity.com/paper/2306.08700/) (2023)
- [Prototypical Cross-domain Knowledge Transfer for Cervical Dysplasia Visual Inspection](https://mlsanity.com/paper/2308.09983/) (2023)
- [Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shifts](https://mlsanity.com/paper/2401.11406/) (2024)
- [Contrastive Centroid Supervision Alleviates Domain Shift in Medical Image Classification](https://mlsanity.com/paper/2205.15658/) (2022)
- [Meta Input: How to Leverage Off-the-Shelf Deep Neural Networks](https://mlsanity.com/paper/2210.13186/) (2022)
- [DAD++: Improved Data-free Test Time Adversarial Defense](https://mlsanity.com/paper/2309.05132/) (2023)
- [SIDE: Self-supervised Intermediate Domain Exploration for Source-free Domain Adaptation](https://mlsanity.com/paper/2310.08928/) (2023)

## Abstract (arXiv)

Domain adaptation aims at training a classifier in one dataset and applying it to a related but not identical dataset. One successfully used framework of domain adaptation is to learn a transformation to match both the distribution of the features (marginal distribution), and the distribution of the labels given features (conditional distribution). In this paper, we propose a new domain adaptation framework named Deep Transfer Network (DTN), where the highly flexible deep neural networks are used to implement such a distribution matching process. This is achieved by two types of layers in DTN: the shared feature extraction layers which learn a shared feature subspace in which the marginal distributions of the source and the target samples are drawn close, and the discrimination layers which match conditional distributions by classifier transduction. We also show that DTN has a computation complexity linear to the number of training samples, making it suitable to large-scale problems. By combining the best paradigms in both worlds (deep neural networks in recognition, and matching marginal and conditional distributions in domain adaptation), we demonstrate by extensive experiments that DTN improves significantly over former methods in both execution time and classification accuracy.