Mohammad Rastegari

I am a senior technical manager in the AI/ML org at the Apple Inc. and an affiliate assistant professor in the Computer Science and Engineering Department at the University of Washington. Previously, I was a research scientist at the Allen Institute for AI (AI2), where I was part of the PRIOR team and I was a co-founder and CTO at

I am one of the creators of xnor-networks: an efficient deep neural network model that uses binary operations for fast inference on resource constraint compute platforms.

Email  /  CV  /  Google Scholar  /  LinkedIn

profile photo

I recieved my Ph.D. from the University of Maryland under the supervision of Prof. Larry S. Davis . My research interest relies on the intersection of computer vision and efficient machine learning.

Selected Publications

For the full list of my publications please visit my Google Scholar page.

Discovering Neural Wirings
M. Worstman, A. Farhadi, M. Rastegari,
NeuroIPS, 2019

Espnet: Efficient spatial pyramid of dilated convolutions for semantic segmentation
S Mehta, M. Rastegari, A Caspi, L Shapiro, H Hajishirzi.
ECCV, 2018

Lcnn: Lookup-based convolutional neural network
H Bagherinezhad, M. Rastegari, A. Farhadi.
CVPR, 2017

Xnor-net: Imagenet classification using binary convolutional neural networks
M. Rastegari, V. Ordonez, J. Redmon, A. Farhadi
ECCV, 2016

Predictable Dual-View Hashing
M. Rastegari J Choi, S Fakhraei, H Daumé III, LS Davis
ICML, 2013

Attribute discovery via predictable discriminative binary codes
M. Rastegari A. Farhadi, David Forsyth
ECCV, 2012