From Selective Deep Convolutional Features to Compact Binary Representations for Image Retrieval
This work addresses efficiency and accuracy challenges in image retrieval for applications like search engines, though it is incremental as it builds on existing CNN and hashing methods.
The paper tackled the problem of large-scale image retrieval by proposing a framework that selects representative local convolutional features using masking strategies and employs embedding and aggregating methods to enhance discriminability, achieving state-of-the-art performance on six benchmarks.
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 (CNN) is proven to be a very powerful tool to extract highly discriminative local descriptors for effective image search. Additionally, in order to further improve the discriminative power of the descriptors, recent works adopt fine-tuned strategies. In this paper, taking a different approach, we propose a novel, computationally efficient, and competitive framework. Specifically, we firstly propose various strategies to compute masks, namely SIFT-mask, 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. Secondly, we propose to employ recent embedding and aggregating methods which 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.