S
Shai Avidan
Researcher at Tel Aviv University
Publications - 153
Citations - 17052
Shai Avidan is an academic researcher from Tel Aviv University. The author has contributed to research in topics: Pixel & Computer science. The author has an hindex of 50, co-authored 138 publications receiving 15378 citations. Previous affiliations of Shai Avidan include Mitsubishi Electric Research Laboratories & Mitsubishi.
Papers
More filters
Posted Content
DeepBBS: Deep Best Buddies for Point Cloud Registration.
TL;DR: DeepBBS as mentioned in this paper is a method for learning a representation that takes into account the best buddy distance between points during training, i.e. pairs of points nearest to each other.
Posted Content
DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction.
TL;DR: Deep Point Correspondence (DPC) as mentioned in this paper uses latent similarity and the input coordinates themselves to construct the point cloud and determine correspondence, replacing the coordinate regression done by the decoder.
Posted Content
Reducing ReLU Count for Privacy-Preserving CNN Speedup.
Inbar Helbitz,Shai Avidan +1 more
TL;DR: In this paper, the ReLU decision of one activation can be used by others, and explore different ways to group activations and different methods to determine the reLU for such a group of activations.
Journal ArticleDOI
Securing Neural Networks with Knapsack Optimization
TL;DR: In this article , the authors propose two ways to accelerate secure inference, one based on the observation that the ReLU outcome of many convolutions is highly correlated and the other based on reducing the number of bit comparisons required for a secure ReLU operation.
Journal ArticleDOI
SAGA: Spectral Adversarial Geometric Attack on 3D Meshes
TL;DR: Tomer et al. as mentioned in this paper proposed a geometric adversarial attack on a 3D mesh autoencoder by forcing it to reconstruct a different geometric shape at its output by perturbing a clean shape in the spectral domain.