Shoot to Know What: An Application of Deep Networks on Mobile Devices
Wu JX(吴家祥); Hu QH(胡庆浩); Leng C(冷聪); Cheng J(程健)
2016-02
会议名称American Association for AI National Conference(AAAI)
会议日期2016-2
会议地点Phoenix, U.S.
摘要Convolutional neural networks (CNNs) have achieved impressive performance in a wide range of computer vision areas. However, the application on mobile devices remains intractable due to the high computation complexity. In this demo, we propose the Quantized CNN (Q-CNN), an efficient framework for CNN models, to fulfill efficient and accurate image classification on mobile devices. Our Q-CNN framework dramatically accelerates the computation and reduces the storage/memory consumption, so that mobile devices can independently run an ImageNet-scale CNN model. Experiments on the ILSVRC-12 dataset demonstrate 4 ∼ 6× speedup and 15 ∼ 20× compression, with merely one percentage drop in the classification accuracy. Based on the Q-CNN framework, 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/173211/14969
专题模式识别国家重点实验室_图像与视频分析
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,Hu QH,Leng C,et al. Shoot to Know What: An Application of Deep Networks on 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
AAAI2016_Shoot to Kn(1243KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wu JX(吴家祥)]的文章
[Hu QH(胡庆浩)]的文章
[Leng C(冷聪)]的文章
百度学术
百度学术中相似的文章
[Wu JX(吴家祥)]的文章
[Hu QH(胡庆浩)]的文章
[Leng C(冷聪)]的文章
必应学术
必应学术中相似的文章
[Wu JX(吴家祥)]的文章
[Hu QH(胡庆浩)]的文章
[Leng C(冷聪)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: AAAI2016_Shoot to Know What, An Application of Deep Networks on Mobile Devices.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。