Next Article in Journal
A New Method of Applying Data Engine Technology to Realize Neural Network Control
Next Article in Special Issue
Refinement of Background-Subtraction Methods Based on Convolutional Neural Network Features for Dynamic Background
Previous Article in Journal
A Source Domain Extension Method for Inductive Transfer Learning Based on Flipping Output
Previous Article in Special Issue
Learning an Efficient Convolution Neural Network for Pansharpening
Open AccessFeature PaperArticle

Triplet Loss Network for Unsupervised Domain Adaptation

Machine Learning and Knowledge Representation Lab in the Institute of Data Science & AI, Innopolis University, Innopolis 420500, Republic of Tatarstan, Russia
College of Technological Innovations, Zayed University, Abu Dhabi 144534, United Arab Emirates
Author to whom correspondence should be addressed.
Algorithms 2019, 12(5), 96;
Received: 25 March 2019 / Revised: 30 April 2019 / Accepted: 2 May 2019 / Published: 8 May 2019
(This article belongs to the Special Issue Deep Learning for Image and Video Understanding)
Domain adaptation is a sub-field of transfer learning that aims at bridging the dissimilarity gap between different domains by transferring and re-using the knowledge obtained in the source domain to the target domain. Many methods have been proposed to resolve this problem, using techniques such as generative adversarial networks (GAN), but the complexity of such methods makes it hard to use them in different problems, as fine-tuning such networks is usually a time-consuming task. In this paper, we propose a method for unsupervised domain adaptation that is both simple and effective. Our model (referred to as TripNet) harnesses the idea of a discriminator and Linear Discriminant Analysis (LDA) to push the encoder to generate domain-invariant features that are category-informative. At the same time, pseudo-labelling is used for the target data to train the classifier and to bring the same classes from both domains together. We evaluate TripNet against several existing, state-of-the-art methods on three image classification tasks: Digit classification (MNIST, SVHN, and USPC datasets), object recognition (Office31 dataset), and traffic sign recognition (GTSRB and Synthetic Signs datasets). Our experimental results demonstrate that (i) TripNet beats almost all existing methods (having a similar simple model like it) on all of these tasks; and (ii) for models that are significantly more complex (or hard to train) than TripNet, it even beats their performance in some cases. Hence, the results confirm the effectiveness of using TripNet for unsupervised domain adaptation in image classification. View Full-Text
Keywords: deep learning; computer vision; domain adaptation; transfer learning; adversarial loss; linear discriminant analysis; representation learning deep learning; computer vision; domain adaptation; transfer learning; adversarial loss; linear discriminant analysis; representation learning
Show Figures

Figure 1

MDPI and ACS Style

Bekkouch, I.E.I.; Youssry, Y.; Gafarov, R.; Khan, A.; Khattak, A.M. Triplet Loss Network for Unsupervised Domain Adaptation. Algorithms 2019, 12, 96.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map

Back to TopTop