Target detection model training method and target detection method and device

Abstract

The invention discloses a training method of a target detection model and a target detection method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the steps of obtaining a plurality of images and an image label corresponding to each image, obtaining a feature vector and a position coding vector corresponding to the image according to the image, obtaining a decoding vector corresponding to the image according to the feature vector and the position coding vector, and decoding the decoding vector corresponding to the image according to the decoding vector. And training by adopting the decoding vectors corresponding to the plurality of images and the image labels to obtain a target detection model. And then the target detection model is used to predict the position and the category of the target in the to-be-detected image. According to the embodiment, the position and the category of the target in the image are detected through the convolutional neural network in combination with the self-attention mechanism, the target detection precision is improved, and the target detection process is simplified.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method for training a target detection model, a method and a device for target detection. Background technique [0002] At present, the methods for commodity detection are mainly divided into two categories: one is to use a two-stage target detection model to detect in commodity scenarios, such as the target detection model represented by Faster-RCNN; the other is to use a single-stage target detection model Carry out commodity detection, such as a series of target detection models represented by YOLO. However, the Convolution Neural Network (CNN) is good at extracting local effective information but cannot extract the long-distance feature relationship between global data, and the calculation process is complicated. [0003] Target detection methods based on the self-attention mechanism mainly include DETR and ViT-FRCNN. However, the DETR method has high computational compl...

AI Technical Summary

Problems solved by technology

However, Convolution Neural Network (CNN) is good at extracting local effective information but cannot extract long-distance feature relationships between global data, and the calculation process is complicated

[0003] Target detection methods based on the self-attention mechanism mainly include DETR and ViT-FRCNN. However, the DETR method has high computational complexity and poor detection effect on small targets. ViT-FRCNN has defects such as complex post-processing operations.

Images