Affine Disentangled GAN for Interpretable and Robust AV Perception
arXiv:1907.05274
Abstract
Autonomous vehicles (AV) have progressed rapidly with the advancements in computer vision algorithms. The deep convolutional neural network as the main contributor to this advancement has boosted the classification accuracy dramatically. However, the discovery of adversarial examples reveals the generalization gap between dataset and the real world. Furthermore, affine transformations may also confuse computer vision based object detectors. The degradation of the perception system is undesirable for safety critical systems such as autonomous vehicles. In this paper, a deep learning system is proposed: Affine Disentangled GAN (ADIS-GAN), which is robust against affine transformations and adversarial attacks. It is demonstrated that conventional data augmentation for affine transformation and adversarial attacks are orthogonal, while ADIS-GAN can handle both attacks at the same time. Useful information such as image rotation angle and scaling factor are also generated in ADIS-GAN. On MNIST dataset, ADIS-GAN can achieve over 98 percent classification accuracy within 30 degrees rotation, and over 90 percent classification accuracy against FGSM and PGD adversarial attack.
References in corpus (8)
- Towards Deep Learning Models Resistant to Adversarial Attacks
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- Synthesizing Robust Adversarial Examples
- Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models
- DeepFool: a simple and accurate method to fool deep neural networks
- Locally Scale-Invariant Convolutional Neural Networks
- Learning Invariant Representations with Local Transformations
- Inferencing Based on Unsupervised Learning of Disentangled Representations