DeepAI AI Chat
Log In Sign Up

Multi-source Distilling Domain Adaptation

11/22/2019
by   Sicheng Zhao, et al.
Renmin University of China
berkeley college
Beijing Didi Infinity Technology and Development Co., Ltd.
8

Deep neural networks suffer from performance decay when there is domain shift between the labeled source domain and unlabeled target domain, which motivates the research on domain adaptation (DA). Conventional DA methods usually assume that the labeled data is sampled from a single source distribution. However, in practice, labeled data may be collected from multiple sources, while naive application of the single-source DA algorithms may lead to suboptimal solutions. In this paper, we propose a novel multi-source distilling domain adaptation (MDDA) network, which not only considers the different distances among multiple sources and the target, but also investigates the different similarities of the source samples to the target ones. Specifically, the proposed MDDA includes four stages: (1) pre-train the source classifiers separately using the training data from each source; (2) adversarially map the target into the feature space of each source respectively by minimizing the empirical Wasserstein distance between source and target; (3) select the source training samples that are closer to the target to fine-tune the source classifiers; and (4) classify each encoded target feature by corresponding source classifier, and aggregate different predictions using respective domain weight, which corresponds to the discrepancy between each source and target. Extensive experiments are conducted on public DA benchmarks, and the results demonstrate that the proposed MDDA significantly outperforms the state-of-the-art approaches. Our source code is released at: https://github.com/daoyuan98/MDDA.

READ FULL TEXT
02/26/2020

Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey

In many practical applications, it is often difficult and expensive to o...
05/24/2017

Robust Data Geometric Structure Aligned Close yet Discriminative Domain Adaptation

Domain adaptation (DA) is transfer learning which aims to leverage label...
10/14/2016

Theoretical Analysis of Domain Adaptation with Optimal Transport

Domain adaptation (DA) is an important and emerging field of machine lea...
01/24/2022

The Enforced Transfer: A Novel Domain Adaptation Algorithm

Existing Domain Adaptation (DA) algorithms train target models and then ...
06/23/2020

Rethinking Distributional Matching Based Domain Adaptation

Domain adaptation (DA) is a technique that transfers predictive models t...
05/03/2018

Boosting Domain Adaptation by Discovering Latent Domains

Current Domain Adaptation (DA) methods based on deep architectures assum...
02/17/2016

Cross-Language Domain Adaptation for Classifying Crisis-Related Short Messages

Rapid crisis response requires real-time analysis of messages. After a d...

Code Repositories

MDDA

Implementation of paper multi-source distilling domain adaptation


view repo