Knowledge Commons of Institute of Automation,CAS
AME: Attention and Memory Enhancement in Hyper-Parameter Optimization | |
Xu, Nuo1,2![]() ![]() ![]() ![]() ![]() ![]() | |
2022 | |
会议名称 | Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR |
会议日期 | 2022.6.19-6.24 |
会议地点 | New Orleans, USA |
摘要 | Training Deep Neural Networks (DNNs) is inherently subject to sensitive hyper-parameters and untimely feedbacks of performance evaluation. To solve these two difficulties, an efficient parallel hyper-parameter optimization model is proposed under the framework of Deep Reinforcement Learning (DRL). Technically, we develop Attention and Memory Enhancement (AME), that includes multi-head attention and memory mechanism to enhance the ability to capture both the short-term and long-term relationships between different hyper-parameter configurations, yielding an attentive sampling mechanism for searching high-performance configurations embedded into a huge search space. During the optimization of transformer-structured configuration searcher, a conceptually intuitive yet powerful strategy is applied to solve the problem of insufficient number of samples due to the untimely feedback. Experiments on three visual tasks, including image classification, object detection, semantic segmentation, demonstrate the effectiveness of AME. |
七大方向——子方向分类 | 机器学习 |
国重实验室规划方向分类 | 视觉信息处理 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/50608 |
专题 | 多模态人工智能系统全国重点实验室_先进时空数据分析与学习 |
通讯作者 | Huo, Chunlei |
作者单位 | 1.NLPR, Institute of Automation, Chinese Academy of Sciences, 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.Huawei Cloud & AI |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Xu, Nuo,Chang, Jianlong,Nie, Xing,et al. AME: Attention and Memory Enhancement in Hyper-Parameter Optimization[C],2022. |
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 | ||
AME Attention and Me(913KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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