Incremental learning method based on image processing model and image processing method

Abstract

The invention provides an incremental learning method based on an image processing model and an image processing method, relates to the technical field of artificial intelligence, in particular to the technical field of computer vision and deep learning, and can be applied to a intelligent city scene. According to the specific implementation scheme, an image processing model to be iterated and an initial incremental network corresponding to the image processing model to be iterated are acquired; respectively inputting a sample image in pre-acquired target sample data into the to-be-iterated image processing model and the initial incremental network to obtain a first image feature and a second image feature respectively corresponding to the to-be-iterated image processing model and the initial incremental network, the target sample data comprises a sample image and corresponding annotation information; generating a fusion feature based on the first image feature and the second image feature; and adjusting network parameters of the initial incremental network based on the difference between the fusion feature and the annotation information corresponding to the sample image. Therefore, a new incremental learning mode is provided.

Description

technical field [0001] The present disclosure relates to the field of artificial intelligence technology, specifically the field of computer vision and deep learning technology, which can be applied in the smart city scene, and especially relates to an incremental learning method and an image processing method based on an image processing model. Background technique [0002] With the rapid development of artificial intelligence technology, deep learning technology has also achieved more and more applications. However, in the existing technology, deep learning models such as neural networks may forget or lose some previously acquired abilities when learning new tasks or adapting to new environments, that is, "catastrophic forgetting". Contents of the invention [0003] Provided are an incremental learning method based on an image processing model, an image processing method, a device, electronic equipment, and a storage medium. [0004] According to the first aspect, an in...

AI Technical Summary

Problems solved by technology

However, in the existing technology, deep learning models such as neural networks will forget or lose some previously acquired abilities when learning new tasks or adapting to new environments, that is, "catastrophic forgetting"

Images