On Minimum Discrepancy Estimation for Deep Domain Adaptation

01/02/2019
by   Mohammad Mahfujur Rahman, et al.
0

In the presence of large sets of labeled data, Deep Learning (DL) has accomplished extraordinary triumphs in the avenue of computer vision, particularly in object classification and recognition tasks. However, DL cannot always perform well when the training and testing images come from different distributions or in the presence of domain shift between training and testing images. They also suffer in the absence of labeled input data. Domain adaptation (DA) methods have been proposed to make up the poor performance due to domain shift. In this paper, we present a new unsupervised deep domain adaptation method based on the alignment of second order statistics (covariances) as well as maximum mean discrepancy of the source and target data with a two stream Convolutional Neural Network (CNN). We demonstrate the ability of the proposed approach to achieve state-of the-art performance for image classification on three benchmark domain adaptation datasets: Office-31 [27], Office-Home [37] and Office-Caltech [8].

READ FULL TEXT
research
07/06/2016

Deep CORAL: Correlation Alignment for Deep Domain Adaptation

Deep neural networks are able to learn powerful representations from lar...
research
06/07/2022

Deep Learning Techniques for Visual Counting

In this dissertation, we investigated and enhanced Deep Learning (DL) te...
research
06/21/2013

Class Proportion Estimation with Application to Multiclass Anomaly Rejection

This work addresses two classification problems that fall under the head...
research
03/23/2016

Lightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction

End-to-end learning methods have achieved impressive results in many are...
research
06/22/2022

Optimal transport meets noisy label robust loss and MixUp regularization for domain adaptation

It is common in computer vision to be confronted with domain shift: imag...
research
09/27/2022

Stacking Ensemble Learning in Deep Domain Adaptation for Ophthalmic Image Classification

Domain adaptation is an attractive approach given the availability of a ...
research
12/11/2017

Can We Teach Computers to Understand Art? Domain Adaptation for Enhancing Deep Networks Capacity to De-Abstract Art

Humans comprehend a natural scene at a single glance; painters and other...

Please sign up or login with your details

Forgot password? Click here to reset