著者
Ali S. Razavian Josephine Sullivan Stefan Carlsson Atsuto Maki
出版者
映像情報メディア学会
雑誌
ITE Transactions on Media Technology and Applications (ISSN:21867364)
巻号頁・発行日
vol.4, no.3, pp.251-258, 2016 (Released:2016-07-01)
参考文献数
39
被引用文献数
196

This paper provides an extensive study on the availability of image representations based on convolutional networks (ConvNets) for the task of visual instance retrieval. Besides the choice of convolutional layers, we present an efficient pipeline exploiting multi-scale schemes to extract local features, in particular, by taking geometric invariance into explicit account, i.e. positions, scales and spatial consistency. In our experiments using five standard image retrieval datasets, we demonstrate that generic ConvNet image representations can outperform other state-of-the-art methods if they are extracted appropriately.