Auto-encoder training method and assembly, and abnormal image detection method and assembly

Abstract

The invention discloses an auto-encoder training method and assembly, and an abnormal image detection method and assembly. In a certain iteration process, the same sample image is utilized to train an auto-encoder, a vector discriminator and a reconstruction discriminator respectively, so that the image reconstruction capability of the auto-encoder can be improved. The vector discriminator is enabled to constrain sample vectors to be approximately uniformly distributed. A reconstruction discriminator is enabled to improve the ability of the reconstruction discriminator to discriminate the original occlusion region and the occlusion region obtained through reconstruction, thereby reducing the possibility of the occurrence of the identical mapping and the generalization ability of the auto-encoder. Finally, the auto-encoder is enabled to have a good reconstruction ability only for a normal image. Therefore, the detection accuracy of the auto-encoder on the abnormal image is improved. Correspondingly, the invention provides an auto-encoder training assembly, an abnormal image detection method and an abnormal image detection assembly, which also have the above technical effects.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to an autoencoder training method and components, and an abnormal image detection method and components. Background technique [0002] Currently, existing autoencoders suffer from identity mapping problems and excessive generalization capabilities. [0003] Identity mapping means: Since the purpose of the autoencoder is to make the output reconstructed picture as similar as possible to the original picture, in the case of insufficient constraints, the autoencoder will tend to directly copy the input to the output, because doing so Best rated. The identity mapping will cause the autoencoder to fail to learn meaningfully, have good reconstruction ability for both normal samples and abnormal samples, and cannot distinguish between the two. [0004] The generalization ability is too strong: when the normal image is similar to the abnormal image, it is difficult for the tra...

AI Technical Summary

Problems solved by technology

The identity mapping will cause the autoencoder to not perform meaningful learning, and it has good reconstruction ability for both normal samples and abnormal samples, and cannot distinguish between the two

Images