Generatively Augmented Neural Network Watchdog for Image Classification Networks. (arXiv:2109.06168v1 [cs.CV])

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.



Related post