FEATURE FUSION BLOCK, CONVOLUTIONAL NEURAL NETWORK, PERSON RE-IDENTIFICATION METHOD, AND RELATED DEVICE

摘要

A multi-scale feature fusion block combined with context information, a convolutional neural network comprising a multi-scale feature fusion block combined with context information, a person re-identification method and apparatus based on the convolutional neural network, a device, and a storage medium. The feature fusion block comprises a forward hierarchical connection group, a backward hierarchical connection group and a channel multi-scale selection module, wherein the forward hierarchical connection group is used for performing information fusion between progressive scales; the backward hierarchical connection group is used for performing information fusion between spanning scales; and the channel multi-scale selection module is used for performing scale feature channel selection on the backward hierarchical connection group. By means of the convolutional neural network, the effective fusion of multi-scale features is realized. By means of the person re-identification method and apparatus, and the device and the storage medium, the person re-identification accuracy can be improved.