Video Not Available
Details
Abstract
This paper proposes a novel residual block to generate a rich set of features for the task of image retrieval. The proposed residual block consists of three modules: a hierarchical spatial feature extraction module focusing on spatial information at different abstraction levels, a multi-scale feature extraction module that generates features at different scales, and a feature fusion module. The results of the experiments show that the proposed residual block noticeably improves the representational capacity of the network, which, in turn, significantly enhances the retrieval performance.