Pedestrian re-identification network training method based on branch learning and layered pseudo label

Abstract

The invention relates to a pedestrian re-identification network training method based on branch learning and layered pseudo labels, wherein a pedestrian re-identification network is a mutual average teaching network. The training method comprises the following steps: obtaining a label data set and a label-free data set, taking the label data set as one layer, dividing the label-free data set into N layers, and assigning the pseudo label to the label-free data of each layer to form N layers of pseudo label data, wherein N is a constant; constructing a branch learning framework comprising N+1 mutual mean-teaching network branches sharing weights, wherein one branch is used for inputting label data for training, and the N layers of pseudo label data are correspondingly input into the other N branches for training; and constructing a loss function of each branch, determining a total loss function of the branch learning framework, performing multiple rounds of training based on the total loss function, and re-layering the label-free data set in each round of training process. Compared with the prior art, the network trained by the invention is more accurate, and the convergence speed of the network during training is high.

Description

technical field [0001] The invention relates to a pedestrian re-identification network training method, in particular to a pedestrian re-identification network training method based on branch learning and layered pseudo-labels. Background technique [0002] Pedestrian re-identification is a task of cross-domain recognition of the same pedestrian, which plays an important role in automatic target recognition. In recent years, many studies have focused on fully supervised person re-identification that requires a large amount of labeled data. However, in daily life, a large amount of labeled data often consumes a lot of manpower and time costs, and in some situations, such as criminal investigations, often There is a lack of a large amount of labeled data, and each pedestrian has only one labeled image for network training. This leads to the meaningful research topic of single-sample person re-identification. [0003] At present, there have been some valuable researches on si...

AI Technical Summary

Problems solved by technology

In fact, the noise of the pseudo-label data makes it unable to provide the same accurate information as the label data, and the pseudo-label data obtained by different pseudo-label methods also have different noises, so they need to be grouped and trained separately

Images