Instance segmentation model training method and device and image processing method and device

Abstract

The invention discloses an instance segmentation model training method and device and an image processing method and device. The training method comprises the following steps: determining a sample image containing at least one target object, wherein the sample image comprises a shape edge point label, a target center point label and a category label of each target object in the at least one targetobject; training a neural network with a branch structure based on the sample image, obtaining the instance segmentation model, wherein the neural network model with the branch structure comprises abackbone network used for feature extraction and a plurality of parallel branch networks located behind the backbone network, the plurality of branch networks comprise a first branch network and a second branch network, the first branch network is used for outputting a classification result of each target object in the at least one target object, and the second branch network is used for outputting a segmentation result of the target object, so that the accuracy and efficiency of an instance segmentation result can be improved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a training method and device for an instance segmentation model, and an image processing method and device. Background technique [0002] In recent years, deep neural networks have achieved excellent performance in automatic understanding of visual signals such as images and videos. In order to understand the semantic information contained in each pixel in the image, object detection and semantic segmentation came into being. Object detection or semantic segmentation can only roughly determine which rectangular detection frame or semantic category of the object the pixel belongs to. In order to achieve more refined image understanding, instance segmentation came into being. On the basis of target detection and semantic segmentation, instance segmentation can further determine which target in which semantic category each pixel in the image belongs to. Instance seg...

AI Technical Summary

Problems solved by technology

[0003] However, when the existing instance segmentation models perform the target detection task and the instance segmentation task, the target detection task is performed first, and then the subsequent instance segmentation task is performed based on the candidate frame obtained by the target detection task, which will make each The segmentation result obtained by the instance is affected by the detection performance of the target detection task, and this will cause the instance segmentation model to have many network parameters, occupy a large memory, and consume a long time, resulting in inaccurate and low efficiency of the instance segmentation result

Images