Domain Adaptation networks for noisy image classification

Master thesis (2017)

Authors

C. Zhang Electrical Engineering, Mathematics and Computer Science

Contributors

J.C. van Gemert (mentor)
S. Pintea (mentor)
Faculty
Electrical Engineering, Mathematics and Computer Science, Electrical Engineering, Mathematics and Computer Science
Copyright: © 2017 Chengqiu Zhang
More Info
expand_more

Published Date

21-08-2017

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Abstract

In this thesis, we propose a novel unsupervised clean-noisy datasets adaptation algorithm based on standard deep learning networks. Specifically, we jointly learn a shared feature encoder for two tasks: 1)supervised classification trained on labeled source (clean) dataset, and 2) unsupervised adaptation to map discriminant features from both source and target domains to a common space. Our proposed network is optimized by a step backpropagation similarly as some of the Generative Adversarial Networks (GANs).

We evaluate our proposed network on two datasets, where a improvement of classification performance is achieved (up to ~19% in average accuracy over all noise levels) over state-of-the-art denoising algorithm BM3D. Interestingly, we also observe that our proposed approach improves the feature transferability on deep networks with its task-specific learning steps.