TWO-STAGE POOLING OF DEEP CONVOLUTIONAL FEATURES FOR IMAGE RETRIEVAL | |
Zhi, Tiancheng ; Duan, Ling-Yu ; Wang, Yitong ; Huang, Tiejun | |
2016 | |
关键词 | image representation image retrieval convolutional neural network feature pooling compact descriptor |
英文摘要 | Convolutional Neural Network (CNN) based image representations have achieved high performance in image retrieval tasks. However, traditional CNN based global representations either provide high dimensional features, which incurs large memory consumption and computing cost, or inadequately capture discriminative information in images, which degenerates the functionality of CNN features. To address those issues, we propose a two-stage partial mean pooling (PMP) approach to construct compact and discriminative global feature representations. The proposed PMP is meant to tackle the limits of traditional max pooling and mean (or average) pooling. By injecting the PMP pooling strategy into the CNN based patch-level mid-level feature extraction and representation, we have significantly improved the state-of-the-art retrieval performance over several common benchmark datasets.; CPCI-S(ISTP); tiancheng.zhi@pku.edu.cn; lingyu@pku.edu.cn; wangyitong@pku.edu.cn; tjhuang@pku.edu.cn; 2465-2469 |
语种 | 英语 |
出处 | 23rd IEEE International Conference on Image Processing (ICIP) |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/459881] |
专题 | 信息科学技术学院 |
推荐引用方式 GB/T 7714 | Zhi, Tiancheng,Duan, Ling-Yu,Wang, Yitong,et al. TWO-STAGE POOLING OF DEEP CONVOLUTIONAL FEATURES FOR IMAGE RETRIEVAL. 2016-01-01. |
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