DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer | |
Yuntao Chen1,5; Naiyan Wang2; Zhaoxiang Zhang1,3,4,5 | |
2018 | |
会议名称 | The Thirty-Second AAAI Conference on Artificial Intelligence, AAAI 2018 |
会议日期 | February 2-7, 2018 |
会议地点 | USA |
摘要 | We have witnessed rapid evolution of deep neural network architecture design in the past years. These latest progresses greatly facilitate the developments in various areas such as computer vision, natural language processing, etc. However, along with the extraordinary performance, these state-of-the-art models also bring in expensive computational cost. Directly deploying these models into applications with real-time requirement is still infeasible. Recently, Hinton et al. (Hinton, Vinyals, and Dean 2014) have shown that the dark knowledge within a powerful teacher model can significantly help the training of a smaller and faster student network. These knowledge are vastly beneficial to improve the generalization ability of the student model. Inspired by their work, we introduce a new type of knowledge – cross sample similarities for model compression and acceleration. This knowledge can be naturally derived from deep metric learning model. To transfer them, we bring the “learning to rank” technique into deep metric learning formulation. We test our proposed DarkRank method on various metric learning tasks including pedestrian re-identification, image retrieval and image clustering. The results are quite encouraging. Our method can improve over the baseline method by a large margin. Moreover, it is fully compatible with other existing methods. When combined, the performance can be further boosted. |
收录类别 | EI |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/20451 |
专题 | 智能感知与计算研究中心 |
通讯作者 | Zhaoxiang Zhang |
作者单位 | 1.Research Center for Brain-inspired Intelligence, CASIA 2.TuSimple 3.National Laboratory of Pattern Recognition, CASIA 4.Center for Excellence in Brain Science and Intelligence Technology, CAS 5.University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Yuntao Chen,Naiyan Wang,Zhaoxiang Zhang. DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer[C],2018. |
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 | ||
darkrank_chen.pdf(378KB) | 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