A novel localized and second order feature coding network for image recognition

Boheng Chen, Jie Li, Gang Wei, Biyun Ma

Abstract: Highlights•We propose an end-to-end model called localized and second-order VLAD Network (LSO-VLADNet) for image recognition.•The proposed network uses an end-to-end dimension reduction layer to ensure the learned feature has low dimension.•The back-propagation models of all the layers are obtained, and the entire network is trained by the end-to-end manner.•Experiments on four image databases demonstrate that the proposed network is very competitive.