Unsupervised Domain Adaptation with Similarity Learning
Author:
- Pedro O. PinheiroPPPedro O. Pinheiro
- 1 June 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 8004-8013
Abstract
The objective of unsupervised domain adaptation is to leverage features from a labeled source domain and learn a classifier for an unlabeled target domain, with a similar but different data distribution. Most deep learning approaches to domain adaptation consist of two steps: (i) learn features that preserve a low risk on labeled samples (source domain) and (ii) make the features from both domains to be as indistinguishable as possible, so that a classifier trained on the source can also be applied on the target domain. In general, the classifiers in step (i) consist of fully-connected layers applied directly on the indistinguishable features learned in (ii). In this paper, we propose a different way to do the classification, using similarity learning. The proposed method learns a pairwise similarity function in which classification can be performed by computing similarity between prototype representations of each category. The domain-invariant features and the categorical prototype representations are learned jointly and in an end-to-end fashion. At inference time, images from the target domain are compared to the prototypes and the label associated with the one that best matches the image is outputed. The approach is simple, scalable and effective. We show that our model achieves state-of-the-art performance in different unsupervised domain adaptation scenarios.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Show and tell: A neural image caption generator2015
- Unsupervised Domain Adaptation by Domain Invariant Projection2013
- Distance-Based Image Classification: Generalizing to New Classes at Near-Zero CostIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- What you saw is not what you get: Domain adaptation using asymmetric kernel transforms2011
- Unbiased look at dataset bias2011
- A theory of learning from different domainsMachine Learning, 2009
- Learning a Similarity Metric Discriminatively, with Application to Face Verification2005
- A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics2002
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Probabilistic Interpretation of Feedforward Classification Network Outputs, with Relationships to Statistical Pattern Recognition1990