A face detection method and storage medium

Abstract

A face detection method and a storage medium, the method comprising the following steps: Step 102, respectively inputting a batch of same training images to a lightweight network and a complex network; Step 104, outputting classification maps for a lightweight network and a complex network As a result, the difficult sample mining method is used for filtering; step 106, constructing a comprehensive loss function, the comprehensive loss function includes a knowledge distillation loss function or a label-based face detection loss function, and the knowledge distillation loss function is based on a lightweight network and a complex The output result of the classification map of the network is obtained; step 108, based on the loss function, update the parameters of the lightweight network, and do not update the parameters of the complex network; step 110, repeat the above steps until the lightweight network is trained to converge. Provide a neural network algorithm for fast parameter adjustment to solve the problem of face detection with lightweight neural network.

Description

technical field [0001] The invention belongs to the technical field of image processing and pattern recognition, and specifically relates to a face detection method, which can be applied to security monitoring, human-computer interaction and many other fields. Background technique [0002] Face detection is an important technique, which is in demand in many computer vision applications, such as face tracking, face alignment, face recognition, etc. In recent years, due to the development of convolutional neural networks, the performance of face detection has been significantly improved. However, existing face detection models are usually computationally slow because they require relatively large neural networks to maintain good face detection performance. Although there are also one-step-based detection frameworks proposed to speed up detection (such as SSD, YOLO), they are still not fast enough for practical application scenarios, especially in CPU-based environments. On t...

AI Technical Summary

Problems solved by technology

[0004] To this end, it is necessary to provide a new type of neural network algorithm that can apply a one-step method to improve the performance of lightweight detection models and quickly adjust parameters to solve the problem of face detection with lightweight neural networks

Images