Robustness-aware 2-bit quantization with real-time performance for neural network

no code implementations • 19 Oct 2020 • XiaoBin Li, Hongxu Jiang, Shuangxi Huang, Fangzheng Tian

The structural information learned from NN not only plays an important role in improving the performance but also allows for further fine tuning of the quantization network by applying the Lipschitz constraint to the structural loss.

Generative Adversarial Network Quantization