Title | ||
---|---|---|
Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations. |
Abstract | ||
---|---|---|
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. |
Year | Venue | Field |
---|---|---|
2017 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017) | Compressibility,Mathematical optimization,End-to-end principle,Learning vector quantization,Theoretical computer science,Vector quantization,Artificial intelligence,Quantization (signal processing),Artificial neural network,Mathematics,Image compression,Machine learning |
DocType | Volume | ISSN |
Conference | 30 | 1049-5258 |
Citations | PageRank | References |
31 | 1.05 | 22 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Eirikur Agustsson | 1 | 257 | 13.89 |
Fabian Mentzer | 2 | 60 | 5.08 |
Michael Tschannen | 3 | 143 | 13.58 |
Cavigelli, L. | 4 | 244 | 22.75 |
Radu Timofte | 5 | 1880 | 118.45 |
Luca Benini | 6 | 13116 | 1188.49 |
Luc Van Gool | 7 | 27566 | 1819.51 |