Generatively Augmented Neural Network Watchdog for Image Classification Networks

TL;DR

This paper enhances neural network watchdogs for image classification by using generative data augmentation to more accurately delineate in-distribution data boundaries, improving out-of-distribution detection.

Contribution

It introduces a generative augmentation method to sharpen the in-distribution boundary in neural network watchdogs, improving out-of-distribution detection accuracy.

Findings

Improved boundary sharpness in in-distribution detection

Enhanced out-of-distribution classification performance

Effective use of generative augmentation for boundary delineation

Abstract

The identification of out-of-distribution data is vital to the deployment of classification networks. For example, a generic neural network that has been trained to differentiate between images of dogs and cats can only classify an input as either a dog or a cat. If a picture of a car or a kumquat were to be supplied to this classifier, the result would still be either a dog or a cat. In order to mitigate this, techniques such as the neural network watchdog have been developed. The compression of the image input into the latent layer of the autoencoder defines the region of in-distribution in the image space. This in-distribution set of input data has a corresponding boundary in the image space. The watchdog assesses whether inputs are in inside or outside this boundary. This paper demonstrates how to sharpen this boundary using generative network training data augmentation thereby bettering the discrimination and overall performance of the watchdog.