Cascade Watchdog: A Multi-tiered Adversarial Guard for Outlier Detection. (arXiv:2108.09375v3 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2108.09375

The identification of out-of-distribution content is critical to the
successful implementation of neural networks. Watchdog techniques have been
developed to support the detection of these inputs, but the performance can be
limited by the amount of available data. Generative adversarial networks have
displayed numerous capabilities, including the ability to generate facsimiles
with excellent accuracy. This paper presents and empirically evaluates a
multi-tiered watchdog, which is developed using GAN generated data, for
improved out-of-distribution detection. The cascade watchdog uses adversarial
training …

arxiv detection lg