Abstract:Many feedforward neural networks generate continuous and piecewise-linear (CPWL) mappings. Specifically, they partition the input domain into regions on which the mapping is an affine function. The number of these so-called linear regions offers a natural metric to characterize the expressiveness of CPWL mappings. Although the precise determination of this quantity is often out of reach, bounds have been proposed for specific architectures, including the well-known ReLU and Maxout networks. In this work, we propose a more general perspective and provide precise bounds on the maximal number of linear regions of CPWL networks based on three sources of expressiveness: depth, width, and activation complexity. Our estimates rely on the combinatorial structure of convex partitions and highlight the distinctive role of depth which, on its own, is able to exponentially increase the number of regions. We then introduce a complementary stochastic framework to estimate the average number of linear regions produced by a CPWL network architecture. Under reasonable assumptions, the expected density of linear regions along any 1D path is bounded by the product of depth, width, and a measure of activation complexity (up to a scaling factor). This yields an identical role to the three sources of expressiveness: no exponential growth with depth is observed anymore.
Abstract:Although 3D point cloud classification has recently been widely deployed in different application scenarios, it is still very vulnerable to adversarial attacks. This increases the importance of robust training of 3D models in the face of adversarial attacks. Based on our analysis on the performance of existing adversarial attacks, more adversarial perturbations are found in the mid and high-frequency components of input data. Therefore, by suppressing the high-frequency content in the training phase, the models robustness against adversarial examples is improved. Experiments showed that the proposed defense method decreases the success rate of six attacks on PointNet, PointNet++ ,, and DGCNN models. In particular, improvements are achieved with an average increase of classification accuracy by 3.8 % on drop100 attack and 4.26 % on drop200 attack compared to the state-of-the-art methods. The method also improves models accuracy on the original dataset compared to other available methods.