Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations
Eirikur Agustsson · Fabian Mentzer · Michael Tschannen · Lukas Cavigelli · Radu Timofte · Luca Benini · Luc V Gool

Mon Dec 4th 06:30 -- 10:30 PM @ Pacific Ballroom #133 #None

We present a new approach to learn compressible representations in deep architectures with an end-to-end training strategy. Our method is based on a soft (continuous) relaxation of quantization and entropy, which we anneal to their discrete counterparts throughout training. We showcase this method for two challenging applications: Image compression and neural network compression. While these tasks have typically been approached with different methods, our soft-to-hard quantization approach gives results competitive with the state-of-the-art for both.

Author Information

Eirikur Agustsson (ETH Zurich)

I am a PhD student at the [Computer Vision Lab]( of [ETH Zurich](, under the supervision of [Prof. Luc Van Gool]( Previously, I received a MSc degree in Electrical Engineering and Information Technology from ETH Zurich and a double BSc degree in Mathematics and Electrical Engineering from the University of Iceland. My main research interests include deep learning for data compression, regression & classification.

Fabian Mentzer (ETH Zurich)
Michael Tschannen (ETH Zurich)
Lukas Cavigelli (ETH Zurich)
Radu Timofte (ETH Zurich)
Luca Benini (ETH Zurich)
Luc V Gool (Computer Vision Lab, ETH Zurich)

More from the Same Authors