Improving the Robustness of Deep Neural Networks via Stability Training
Venue
CVPR'2016, IEEE (to appear)
Publication Year
2016
Authors
Stephan Zheng, Yang Song, Thomas Leung, Ian Goodfellow
BibTeX
Abstract
In this paper we address the issue of output instability of deep neural networks:
small perturbations in the visual input can significantly distort the feature
embeddings and output of a neural network. Such instability affects many deep
architectures with state-of-the-art performance on a wide range of computer vision
tasks. We present a general stability training method to stabilize deep networks
against small input distortions that result from various types of common image
processing, such as compression, rescaling, and cropping. We validate our method by
stabilizing the stateof-the-art Inception architecture [11] against these types of
distortions. In addition, we demonstrate that our stabilized model gives robust
state-of-the-art performance on largescale near-duplicate detection, similar-image
ranking, and classification on noisy datasets.
