Image Synthesis with a Single (Robust) Classifier

by   Shibani Santurkar, et al.

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


Computer Vision with a Single (Robust) Classifier

We show that the basic classification framework alone can be used to tac...

Robust Certification for Laplace Learning on Geometric Graphs

Graph Laplacian (GL)-based semi-supervised learning is one of the most u...

MAGIC: Mask-Guided Image Synthesis by Inverting a Quasi-Robust Classifier

We offer a method for one-shot image synthesis that allows controlling m...

Introspective Classifier Learning: Empower Generatively

In this paper we propose introspective classifier learning (ICL) that em...

Robust Classification using Robust Feature Augmentation

Existing deep neural networks, say for image classification, have been s...

On the Benefits of Attributional Robustness

Interpretability is an emerging area of research in trustworthy machine ...

MIRST-DM: Multi-Instance RST with Drop-Max Layer for Robust Classification of Breast Cancer

Robust self-training (RST) can augment the adversarial robustness of ima...

Code Repositories


Notebooks for reproducing the paper "Computer Vision with a Single (Robust) Classifier"

view repo