2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information
Login Paper Search My Schedule Paper Index Help

My ICASSP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDMLSP-3.1
Paper Title EVOLUTIONARY QUANTIZATION OF NEURAL NETWORKS WITH MIXED-PRECISION
Authors Zhenhua Liu, Peking University, China; Xinfeng Zhang, University of Chinese Academy of Sciences, China; Shanshe Wang, Siwei Ma, Wen Gao, Peking University, China
SessionMLSP-3: Deep Learning Training Methods 3
LocationGather.Town
Session Time:Tuesday, 08 June, 13:00 - 13:45
Presentation Time:Tuesday, 08 June, 13:00 - 13:45
Presentation Poster
Topic Machine Learning for Signal Processing: [MLR-DEEP] Deep learning techniques
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Quantization is an effective way for reducing the memory and computation costs of deep neural networks. Most of existing methods exploit the fixed-precision quantization approach, e.g., weights and activations (i.e., output features) are represented as 8-bit values. Although mixed-precision quantization provides us a greater possibility to efficiently allocate computation resources and maintain the network performance, it is difficult to accurately solve the optimal bit-width of each layer. In this paper, we develop a novel evolutionary based method to automatically determine the bit-widths of weights and activations in each convolutional layer, namely, Evolutionary Mixed-Precision Quantization (EMQ). Specifically, the quantization intervals of weights and activations of all layers in the given network will be simultaneously encoded as an individual. The fitness of each individual is calculated as the performance of the corresponding quantized network. The optimal quantization result will be updated and elected during the evolutionary search. Extensive experiments conducted on benchmark datasets and models demonstrate the effectiveness of the proposed method over the state-of-the-art network quantization algorithms.