Abstract

Recently, convolutional neural networks (CNN) have demonstrated impressive performance in various computer vision tasks. However, high performance hardware is typically indispensable for the application of CNN models due to the high computation complexity, which prohibits their further extensions. In this paper, we propose an effifi- cient framework, namely Quantized CNN, to simultaneously speed-up the computation and reduce the storage and memory overhead of CNN models. Both fifilter kernels in convolutional layers and weighting matrices in fully-connected layers are quantized, aiming at minimizing the estimation error of each layer’s response. Extensive experiments on the ILSVRC-12 benchmark demonstrate 4 ∼ 6× speed-up and 15 ∼ 20× compression with merely one percentage loss of classifification accuracy. With our quantized CNN model, even mobile devices can accurately classify images within one second.