Fine-residual VLAD for image retrieval

详细信息    查看全文

• 作者：Ziqiong Liu^aAuthor Vitae ; Shengjin Wang^a ; ^{wgsgj@tsinghua.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Qi Tian^bAuthor Vitae
• 关键词：VLAD ; Image retrieval ; Residual codebook ; Fine residual
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：15 January 2016
• 年：2016
• 卷：173
• 期：part_P3
• 页码：1183-1191
• 全文大小：3692 K

文摘

This paper revisits the vector of locally aggregated descriptors (VLAD), which aggregates the residuals of local descriptors to their cluster centers. Since VLAD usually adopts a small-size codebook, the clusters are coarse and residuals not discriminative. To address this problem, this paper proposes to generate a number of residual codebooks descended from the original clusters. After quantizing local descriptors with these codebooks, we pool the resulting secondary residuals as well as the primary ones to obtain the fine residuals. We show that, with two-step aggregation, the fine-residual VLAD has the same dimension as the original. Experiments on two image search benchmarks confirm the improved discriminative power of our method: we observe consistent superiority to the baseline and competitive performance to the state-of-the-arts.