Spotlight

Tue 12:30

Mind the Pad -- CNNs Can Develop Blind Spots
Bilal Alsallakh · Narine Kokhlikyan · Vivek Miglani · Jun Yuan · Orion Reblitz-Richardson

Spotlight

Tue 3:45

Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphs
Pim De Haan · Maurice Weiler · Taco Cohen · Max Welling

Poster

Wed 1:00

Simple Spectral Graph Convolution
Hao Zhu · Piotr Koniusz

Poster

Tue 1:00

Hyperbolic Neural Networks++
Ryohei Shimizu · YUSUKE Mukuta · Tatsuya Harada

Poster

Tue 17:00

Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets?
Zhiyuan Li · Yi Zhang · Sanjeev Arora

Poster

Wed 9:00

Orthogonalizing Convolutional Layers with the Cayley Transform
Asher Trockman · Zico Kolter

Poster

Wed 9:00

More or Less: When and How to Build Convolutional Neural Network Ensembles
Abdul Wasay · Stratos Idreos

Poster

Mon 9:00

Vector-output ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomial-time Algorithms
Arda Sahiner · Tolga Ergen · John M Pauly · Mert Pilanci

Poster

Mon 1:00

Isometric Transformation Invariant and Equivariant Graph Convolutional Networks
Masanobu Horie · Naoki Morita · Toshiaki Hishinuma · Yu Ihara · Naoto Mitsume

Poster

Mon 9:00

Trajectory Prediction using Equivariant Continuous Convolution
Robin Walters · Jinxi Li · Rose Yu

Poster

Mon 1:00

PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences
Hehe Fan · Xin Yu · Yuhang Ding · Yi Yang · Mohan Kankanhalli

Spotlight

Tue 19:25

Orthogonalizing Convolutional Layers with the Cayley Transform
Asher Trockman · Zico Kolter