Flexible separable convolution framework and feature extraction method and its application in vgg and resnet

Abstract

The invention discloses a flexible and separable convolution framework and feature extraction method and its application in VGG and ResNet, including a feature map clustering and division module, a first convolution operation module, a second convolution operation module, and feature map fusion module and attention mechanism SE module; the feature map clustering and division module divides the feature map into feature maps representing main information and feature maps representing supplementary information; the first convolution operation module performs ordinary convolution operations on feature maps representing main information; the second The second convolution operation module performs group convolution operation on the feature map representing the supplementary information; the feature map fusion module first stitches the convolutional feature map and then adds and activates the original feature map; the attention mechanism SE module will extract the channel weight Multiplied with the feature map to generate the output feature map. The invention includes ordinary convolution, group convolution, residual branch and attention mechanism SE, which reduces the amount of calculation and network parameters while ensuring the accuracy of the operation, and can be plugged and used in the neural network convolution layer middle.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a flexible and separable convolution framework and feature extraction method and its application in VGG and ResNet. Background technique [0002] In recent years, deep convolutional neural networks have shown excellent performance on different computer vision tasks such as image recognition, object detection, and semantic segmentation. However, traditional deep convolutional neural networks require a large number of parameters and floating-point operations to achieve satisfactory accuracy, and the model inference time is long. In some real application scenarios, such as mobile or embedded devices, due to the limited memory and computing resources of the device, the actual deployment of traditional deep convolutional neural networks in small devices is difficult; at the same time, the actual application requirements for low latency are difficult. Satisfy. Although the h...

AI Technical Summary

Problems solved by technology

However, traditional deep convolutional neural networks require a large number of parameters and floating-point operations to achieve satisfactory accuracy, and the model inference time is long

In some real application scenarios, such as mobile or embedded devices, due to the limited memory and computing resources of the device, the actual deployment of traditional deep convolutional neural networks in small devices is difficult; at the same time, the actual application requirements for low latency are difficult. Satisfy

Images