Generatively Augmented Neural Network Watchdog for Image Classification Networks
This addresses a critical safety issue for deploying classification networks in real-world applications, but it is incremental as it builds on existing watchdog techniques.
The paper tackles the problem of identifying out-of-distribution data in image classification networks by sharpening the boundary using generative network training data augmentation, resulting in improved discrimination and overall performance of the watchdog.
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.