Learning Target-Domain-Specific Classifier for Partial Domain Adaptation
- 4 June 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 32 (5) , 1989-2001
Abstract
Unsupervised domain adaptation (UDA) aims at reducing the distribution discrepancy when transferring knowledge from a labeled source domain to an unlabeled target domain. Previous UDA methods assume that the source and target domains share an identical label space, which is unrealistic in practice since the label information of the target domain is agnostic. This article focuses on a more realistic UDA scenario, i.e., partial domain adaptation (PDA), where the target label space is subsumed to the source label space. In the PDA scenario, the source outliers that are absent in the target domain may be wrongly matched to the target domain (technically named negative transfer), leading to performance degradation of UDA methods. This article proposes a novel target-domain-specific classifier learning-based domain adaptation (TSCDA) method. TSCDA presents a soft-weighed maximum mean discrepancy criterion to partially align feature distributions and alleviate negative transfer. Also, it learns a target-specific classifier for the target domain with pseudolabels and multiple auxiliary classifiers to further address the classifier shift. A module named peers-assisted learning is used to minimize the prediction difference between multiple target-specific classifiers, which makes the classifiers more discriminant for the target domain. Extensive experiments conducted on three PDA benchmark data sets show that TSCDA outperforms other state-of-the-art methods with a large margin, e.g., 4% and 5.6% averagely on Office-31 and Office-Home, respectively.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (61976229, 61906046, 11631015, U1611265)
- Science and Technology Program of Guangzhou (201804010248)
This publication has 32 references indexed in Scilit:
- Correlation Alignment for Unsupervised Domain Adaptation2017
- Deep Hashing Network for Unsupervised Domain Adaptation2017
- Adversarial Discriminative Domain Adaptation2017
- Deep Residual Learning for Image Recognition2016
- Going deeper with convolutions2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Adapting Visual Category Models to New Domains2010
- A theory of learning from different domainsMachine Learning, 2009
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- A database for handwritten text recognition researchIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994