AdaSTE: An Adaptive Straight-Through Estimator to Train Binary Neural Networks
Paper in proceeding, 2022
bilevel optimization
backpropagation
straight-through estimator
Binary Neural Networks
Author
Huu Le
Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering
Rasmus Kjær Høier
Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering
Che-Tsung Lin
Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering
Christopher Zach
Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
10636919 (ISSN)
Vol. 2022-June 460-469978-166546946-3 (ISBN)
New Orleans, USA,
Subject Categories
Computer Vision and Robotics (Autonomous Systems)
DOI
10.1109/CVPR52688.2022.00055