Search Results for author: Shachar Fleishman

Found 4 papers, 2 papers with code

Generative Low-Shot Network Expansion

no code implementations ICLR 2018 Adi Hayat, Mark Kliger, Shachar Fleishman, Daniel Cohen-Or

We present a simple yet powerful hard distillation method where the base network is augmented with additional weights to classify the novel classes, while keeping the weights of the base network unchanged.

MeshCNN: A Network with an Edge

1 code implementation16 Sep 2018 Rana Hanocka, Amir Hertz, Noa Fish, Raja Giryes, Shachar Fleishman, Daniel Cohen-Or

In this paper, we utilize the unique properties of the mesh for a direct analysis of 3D shapes using MeshCNN, a convolutional neural network designed specifically for triangular meshes.

3D Part Segmentation Cube Engraving Classification

Novelty Detection with GAN

no code implementations ICLR 2018 Mark Kliger, Shachar Fleishman

The ability of a classifier to recognize unknown inputs is important for many classification-based systems.

General Classification Novelty Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.