Multi-level image representation for large-scale image-based instance retrieva

作     者：Qili Deng Shuai Wu Jie Wen Yong Xu Qili Deng;Shuai Wu;Jie Wen;Yong Xu

作者机构：Bio-computing Research Center Shenzhen Graduate School Harbin Institute of Technology Shenzhen 518055People's Republic of China 

出 版 物：《CAAI Transactions on Intelligence Technology》 (智能技术学报（英文）)

年 卷 期：2018年第3卷第1期

页      面：33-39页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 080203[工学-机械设计及理论] 0835[工学-软件工程] 0802[工学-机械工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Shenzhen Municipal Science and Technology Innovation Council Shenzhen Municipal Science and Technology Innovation Council, (2016TX03X164) 

主　　题：图像检索 神经网络 科学研究 发展现状 

摘      要：In recent years, instance-level-image retrieval has attracted massive attention. Several researchers proposed that the representations learned by convolutional neural network （CNN） can be used for image retrieval task. In this study, the authors propose an effective feature encoder to extract robust information from CNN. It consists of two main steps： the embedding step and the aggregation step. Moreover, they apply the multi-task loss function to train their model in order to make the training process more effective. Finally, this study proposes a novel representation policy that encodes feature vectors extracted from different layers to capture both local patterns and semantic concepts from deep CNN. They call this ＇multi-level-image representation＇, which could further improve the performance. The proposed model is helpful to improve the retrieval performance. For the sake of comprehensively evaluating the performance of their approach, they conducted ablation experiments with various convolutional NN architectures. Furthermore, they apply their approach to a concrete challenge - Alibaba large-scale search challenge. The results show that their model is effective and competitive.