资源分类
》 资源 》论文》Image Synthesis with a Single (Robust) Classifier

Image Synthesis with a Single (Robust) Classifier

2020-02-25 | |  135 |   38 |   0

Abstract

We show that the basic classification framework alone can be used to tackle some of the most challenging tasks in image synthesis. In contrast to other state-of-theart approaches, the toolkit we develop is rather minimal: it uses a single, off-theshelf classifier for all these tasks. The crux of our approach is that we train this classifier to be adversarially robust. It turns out that adversarial robustness is precisely what we need to directly manipulate salient features of the input. Overall, our findings demonstrate the utility of robustness in the broader machine learning context.2

上一篇：Approximate Feature Collisions in Neural Nets

下一篇：Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...