TL;DR本文提出基于多层级相似度计算的、高效的全卷积 Siamese 网络,使用卷积层、空间变形网络和深度可分离卷积等技术,在 Person Re-Identification 问题上实现有效的结果。
Abstract
person re-identification (ReID) requires comparing two images of person
captured under different conditions. Existing work based on neural networks
often computes the similarity of feature maps from one single convolutional
layer. In this work, we propose an efficient, end-to-end fully