Quantized Convolutional Neural Networks for Mobile Devices

	Quantized Convolutional Neural Networks for Mobile Devices
	Wu JX(吴家祥); Leng C(冷聪); Wang YH(王宇航); Hu QH(胡庆浩); Cheng J(程健)
	2016-06
会议名称	IEEE Conference on Computer Vision and Pattern Recognition
会议日期	2016-6
会议地点	Las Vegas, U.S.
摘要	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 efficient framework, namely Quantized CNN, to simultaneously speed-up the computation and reduce the storage and memory overhead of CNN models. Both filter 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 classification accuracy. With our quantized CNNmodel, even mobile devices can accurately classify images within one second.
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/14970
专题	紫东太初大模型研究中心_图像与视频分析
作者单位	中国科学院自动化研究所
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Wu JX,Leng C,Wang YH,et al. Quantized Convolutional Neural Networks for Mobile Devices[C],2016.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
CVPR2016_Quantized C（321KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载