DeepAI AI Chat
Log In Sign Up

Safer Classification by Synthesis

by   William Wang, et al.

The discriminative approach to classification using deep neural networks has become the de-facto standard in various fields. Complementing recent reservations about safety against adversarial examples, we show that conventional discriminative methods can easily be fooled to provide incorrect labels with very high confidence to out of distribution examples. We posit that a generative approach is the natural remedy for this problem, and propose a method for classification using generative models. At training time, we learn a generative model for each class, while at test time, given an example to classify, we query each generator for its most similar generation, and select the class corresponding to the most similar one. Our approach is general and can be used with expressive models such as GANs and VAEs. At test time, our method accurately "knows when it does not know," and provides resilience to out of distribution examples while maintaining competitive performance for standard examples.


page 8

page 9

page 10


Conditional Generative Models are not Robust

Class-conditional generative models are an increasingly popular approach...

"Prompt-Gamma Neutron Activation Analysis (PGNAA)" Metal Spectral Classification using Deep Learning Method

There is a pressing market demand to minimize the test time of Prompt Ga...

Generating Natural Language Adversarial Examples on a Large Scale with Generative Models

Today text classification models have been widely used. However, these c...

Adversarial Feedback Loop

Thanks to their remarkable generative capabilities, GANs have gained gre...

Kernel Mean Matching for Content Addressability of GANs

We propose a novel procedure which adds "content-addressability" to any ...

Re-using Adversarial Mask Discriminators for Test-time Training under Distribution Shifts

Thanks to their ability to learn flexible data-driven losses, Generative...

Tractable Generative Convolutional Arithmetic Circuits

Casting neural networks in generative frameworks is a highly sought-afte...