Deep Transfer Network: Unsupervised Domain Adaptation

03/02/2015
by   Xu Zhang, et al.
0

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.

READ FULL TEXT

page 4

page 9

research
06/24/2019

Bayesian Uncertainty Matching for Unsupervised Domain Adaptation

Domain adaptation is an important technique to alleviate performance deg...
research
07/17/2020

Learning to Match Distributions for Domain Adaptation

When the training and test data are from different distributions, domain...
research
07/01/2021

Mitigating Uncertainty of Classifier for Unsupervised Domain Adaptation

Understanding unsupervised domain adaptation has been an important task ...
research
07/19/2018

Visual Domain Adaptation with Manifold Embedded Distribution Alignment

Visual domain adaptation aims to learn robust classifiers for the target...
research
05/13/2022

Unsupervised Structure-Texture Separation Network for Oracle Character Recognition

Oracle bone script is the earliest-known Chinese writing system of the S...
research
01/03/2023

Heterogeneous Domain Adaptation and Equipment Matching: DANN-based Alignment with Cyclic Supervision (DBACS)

Process monitoring and control are essential in modern industries for en...
research
02/16/2016

Unsupervised Domain Adaptation Using Approximate Label Matching

Domain adaptation addresses the problem created when training data is ge...

Please sign up or login with your details

Forgot password? Click here to reset