Model training method, image segmentation method, devices, electronic equipment and medium

Abstract

The embodiment of the invention discloses an image segmentation model training method and device, an image segmentation method and device, electronic equipment and a medium. According to one specificembodiment of the invention, the method comprises the steps that: a training sample is selected from a training sample set, wherein the training sample comprises a sample image and a label of the sample image, wherein the label comprises a segmentation result of the sample image and contour information of the sample image; the sample image of the selected training sample is inputted into an imagesegmentation model, so that an actual segmentation result and actual contour information can be obtained; the difference between the actual segmentation result and the segmentation result in the labelis determined based on a preset loss function, so that a first loss value is obtained; based on the loss function, the difference between the actual contour information and the contour information inthe label is determined, so that a second loss value is obtained; and in response to determining that the image segmentation model is not trained completely, parameters of the image segmentation model are adjusted based on the first loss value and the second loss value. With the method of the embodiment adopted, the accuracy of the model segmentation result is improved.

Description

technical field [0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular to an image segmentation model training method, an image segmentation method, a device, an electronic device, and a computer-readable medium. Background technique [0002] Image segmentation can divide an image into multiple regions. As an example, segmenting face regions in an image is a common image segmentation scenario. In practice, image segmentation is often achieved through image segmentation models. These image segmentation models need to improve accuracy in some scenarios. For example, in the scene of face segmentation, the obtained face regions are often not accurate enough. Contents of the invention [0003] The Summary of the Disclosure is provided to introduce concepts in a simplified form that are described in detail in the Detailed Description that follows. The content of this disclosure is not intended to identify the key featur...

AI Technical Summary

Problems solved by technology

For example, in the scene of face segmentation, t

Images