Image classification model training method and image processing method and device

Abstract

The invention discloses an image classification model training method and image processing method and device. The method comprises the steps of obtaining a to-be-trained image; when the first model parameter of the offset network to be trained is fixed, obtaining first prediction class marking information of the image to be trained through the image classification network to be trained; determining a second model parameter by adopting a classification loss function according to the image content category information and the first prediction category annotation information; When a second modelparameter of the to-be-trained image classification network is fixed, obtaining second prediction class marking information of the to-be-trained image through the to-be-trained offset network; Determining a third model parameter by adopting a classification loss function according to the image content category information and the second prediction category annotation information; And obtaining animage semantic segmentation network model according to the second model parameter and the third model parameter. The invention further discloses an image processing method and device. According to themethod and the device, manual pixel level marking is not needed, so that the manual marking cost is reduced, and the model training efficiency is improved.

Description

technical field [0001] The present application relates to the field of artificial intelligence, in particular to a method for training an image classification model, an image processing method and a device. Background technique [0002] Image semantic segmentation is the cornerstone technology of image understanding, and plays a pivotal role in autonomous driving systems (such as street view recognition and understanding), drone applications (such as landing point judgment) and wearable device applications. An image is composed of many pixels, and semantic segmentation is to segment the pixels according to the different semantic meanings expressed in the image, so that the machine can automatically segment and recognize the content in the image. [0003] At present, a deep convolutional neural network is usually trained to achieve full-image classification, and then the corresponding image content area in the image to be trained is located according to the deep convolutional...

AI Technical Summary

Problems solved by technology

Taking an image to be trained with a resolution of 1024×2048 as an example, it usually takes 1.5 hours to manually label an image with this resolution at the pixel level, which leads to high manual labeling costs and low model training efficiency

Images