Reinforcement Learning-based Layer-wise Quantization For Lightweight Deep Neural Networks

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 9
  • Download : 0
Network quantization has been widely studied to compress the deep neural network in mobile devices. Conventional methods quantize the network parameters of all layers with the same fixed precision, regardless of the number of parameters in each layer. However, quantizing the weights of the layer with many parameters is more effective in reducing the model size. Accordingly, in this paper, we propose a novel mixed-precision quantization method based on reinforcement learning. Specifically, we utilize the number of parameters at each layer as a prior for our framework. By using the accuracy and the bit-width as a reward, the proposed framework determines the optimal quantization policy for each layer. By applying this policy sequentially, we achieve weighted-average 2.97 bits for the VGG-16 model on the CIFAR-10 dataset with no degradation of the accuracy, compared with its full-precision baseline. We also show that our framework can provide an optimal quantization policy for the VGG-Net and the ResNet to minimize the storage while preserving the accuracy.
Publisher
IEEE Signal Processing Society
Issue Date
2020-10-26
Language
English
Citation

2020 IEEE International Conference on Image Processing (ICIP)

DOI
10.1109/ICIP40778.2020.9191267
URI
http://hdl.handle.net/10203/278681
Appears in Collection
EE-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0