Semi-supervised Deep Domain Adaptation via Coupled Neural Networks
- 27 June 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 27 (11) , 5214-5224
Abstract
Domain adaptation is a promising technique when addressing limited or no labeled target data by borrowing well-labeled knowledge from the auxiliary source data. Recently, researchers have exploited multi-layer structures for discriminative feature learning to reduce the domain discrepancy. However, there are limited research efforts on simultaneously building a deep structure and a discriminative classifier over both labeled source and unlabeled target. In this paper, we propose a semi-supervised deep domain adaptation framework, in which the multi-layer feature extractor and a multi-class classifier are jointly learned to benefit from each other. Specifically, we develop a novel semi-supervised class-wise adaptation manner to fight off the conditional distribution mismatch between two domains by assigning a probabilistic label to each target sample, i.e., multiple class labels with different probabilities. Furthermore, a multi-class classifier is simultaneously trained on labeled source and unlabeled target samples in a semi-supervised fashion. In this way, the deep structure can formally alleviate the domain divergence and enhance the feature transferability. Experimental evaluations on several standard cross-domain benchmarks verify the superiority of our proposed approach.Keywords
Funding Information
- National Science Foundation (1651902)
- Office of Naval Research (N00014-14-1-0484)
- Army Research Office (W911NF-17-1-0367)
This publication has 32 references indexed in Scilit:
- Missing Modality Transfer Learning via Latent Low-Rank ConstraintIEEE Transactions on Image Processing, 2015
- Feature Space Independent Semi-Supervised Domain Adaptation via Kernel MatchingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Transfer Learning for Visual Categorization: A SurveyIEEE Transactions on Neural Networks and Learning Systems, 2014
- Learning Deep Hierarchical Visual Feature CodingIEEE Transactions on Neural Networks and Learning Systems, 2014
- Generalized Transfer Subspace Learning Through Low-Rank ConstraintInternational Journal of Computer Vision, 2014
- Unsupervised Adaptation Across Domain Shifts by Generating Intermediate Data RepresentationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Generalized Domain-Adaptive Dictionaries2013
- Exploiting associations between word clusters and document classes for cross‐domain text categorization†Statistical Analysis and Data Mining: An ASA Data Science Journal, 2010
- Adapting Visual Category Models to New Domains2010
- A theory of learning from different domainsMachine Learning, 2009