no code implementations • 2 Sep 2020 • Sean I. Young, Wang Zhe, David Taubman, Bernd Girod
In this paper, we compress convolutional neural network (CNN) weights post-training via transform quantization.
no code implementations • 25 Sep 2019 • Zhe Wang, Jie Lin, Mohamed M. Sabry Aly, Sean I Young, Vijay Chandrasekhar, Bernd Girod
In this paper, we address an important problem of how to optimize the bit allocation of weights and activations for deep CNNs compression.
1 code implementation • CVPR 2019 • Donald G. Dansereau, Bernd Girod, Gordon Wetzstein
Feature detectors and descriptors are key low-level vision tools that many higher-level tasks build on.
no code implementations • 10 Apr 2018 • Jean-Baptiste Boin, Andre Araujo, Bernd Girod
The task of person re-identification has recently received rising attention due to the high performance achieved by new methods based on deep learning.
no code implementations • CVPR 2013 • Huizhong Chen, Andrew C. Gallagher, Bernd Girod
We show that describing people in terms of similarity to a vector of possible first names is a powerful description of facial appearance that can be used for face naming and building facial attribute classifiers.
no code implementations • ECCV 2012 • Huizhong Chen, Andrew Gallagher, Bernd Girod
Describing clothing appearance with semantic attributes is an appealing technique for many important applications.