papers AI Learner
The Github is limit! Click to go to the new site.

Efficient Multi-Domain Dictionary Learning with GANs

2018-11-01
Cho Ying Wu, Ulrich Neumann

Abstract

In this paper, we propose the multi-domain dictionary learning (MDDL) to make dictionary learning-based classification more robust to data representing in different domains. We use adversarial neural networks to generate data in different styles, and collect all the generated data into a miscellaneous dictionary. To tackle the dictionary learning with many samples, we compute the weighting matrix that compress the miscellaneous dictionary from multi-sample per class to single sample per class. We show that the time complexity solving the proposed MDDL with weighting matrix is the same as solving the dictionary with single sample per class. Moreover, since the weighting matrix could help the solver rely more on the training data, which possibly lie in the same domain with the testing data, the classification could be more accurate.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1811.00274

PDF

https://arxiv.org/pdf/1811.00274


Similar Posts

Comments