Dynamic Dual Gating Neural Networks | |
Li, Fanrong1,2; Li, Gang1; He, Xiangyu1; Cheng, Jian1,2,3 | |
2021 | |
会议日期 | 2021 |
会议地点 | Online |
英文摘要 | In dynamic neural networks that adapt computations to different inputs, gating-based methods have demonstrated notable generality and applicability in trading-off the model complexity and accuracy. However, existing works only explore the redundancy from a single point of the network, limiting the performance. In this paper, we pro- pose dual gating, a new dynamic computing method, to re- duce the model complexity at run-time. For each convolutional block, dual gating identifies the informative features along two separate dimensions, spatial and channel. Specifically, the spatial gating module estimates which areas are essential, and the channel gating module predicts the salient channels that contribute more to the results. Then the computation of both unimportant regions and irrelevant channels can be skipped dynamically during inference. Extensive experiments on a variety of datasets demonstrate that our method can achieve higher accuracy under similar computing budgets compared with other dynamic execution methods. In particular, dynamic dual gat- ing can provide 59.7% saving in computing of ResNet50 with 76.41% top-1 accuracy on ImageNet, which has advanced the state-of-the-art. Codes are available at https://github.com/lfr-0531/DGNet. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/48624] |
专题 | 类脑芯片与系统研究 |
通讯作者 | Cheng, Jian |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.School of Future Technology, University of Chinese Academy of Sciences 3.CAS Center for Excellence in Brain Science and Intelligence Technology |
推荐引用方式 GB/T 7714 | Li, Fanrong,Li, Gang,He, Xiangyu,et al. Dynamic Dual Gating Neural Networks[C]. 见:. Online. 2021. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论