From Selective Deep Convolutional Features to Compact Binary Representations for Image Retrieval

Document Type

Article

Publication Date

6-5-2019

Publication Source

ACM Transactions on Multimedia Computing, Communications and Applications

Abstract

In the large-scale image retrieval task, the two most important requirements are the discriminability of image representations and the efficiency in computation and storage of representations. Regarding the former requirement, Convolutional Neural Network is proven to be a very powerful tool to extract highly discriminative local descriptors for effective image search. Additionally, to further improve the discriminative power of the descriptors, recent works adopt fine-tuned strategies. In this article, taking a different approach, we propose a novel, computationally efficient, and competitive framework. Specifically, we first propose various strategies to compute masks, namely, SIFT-masks, SUM-mask, and MAX-mask, to select a representative subset of local convolutional features and eliminate redundant features. Our in-depth analyses demonstrate that proposed masking schemes are effective to address the burstiness drawback and improve retrieval accuracy. Second, we propose to employ recent embedding and aggregating methods that can significantly boost the feature discriminability. Regarding the computation and storage efficiency, we include a hashing module to produce very compact binary image representations. Extensive experiments on six image retrieval benchmarks demonstrate that our proposed framework achieves the state-of-the-art retrieval performances.

ISBN/ISSN

1551-6857

Publisher

Association for Computing Machinery

Volume

15

Issue

2

Keywords

Content based image retrieval, image hashing, embedding, aggregating, deep convolutional features, unsupervised

Link to Full Text

Share

COinS