Image Synthesis with a Single (Robust) Classifier

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-the-art approaches, the toolkit we develop is rather minimal: it uses a single, off-the-shelf 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. Code and models for our experiments can be found at https://git.io/robust-apps.

PDF Abstract NeurIPS 2019 PDF NeurIPS 2019 Abstract

Datasets


Results from the Paper


Ranked #63 on Image Generation on CIFAR-10 (Inception score metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Generation CIFAR-10 Single Classifier Inception score 7.5 # 63

Methods


No methods listed for this paper. Add relevant methods here