Pretrained large-scale AI models need to 'forget' specific information for privacy and computational efficiency, but no methods exist for doing so in black-box vision-language models ...

A novel approach called 'black-box forgetting' enhances vision-language classifiers, allowing selective class forgetting to boost AI efficiency and accuracy.

Researchers have highlighted that using deep learning to classify myopia severity can support large-scale screening in ...

It can input target images into a pre-trained basic classification model to extract vehicle image features, classification results, and confidence levels. This process not only enhances the accuracy ...

The method includes: inputting a target image into a pre-trained basic classification model to obtain the image features of the target image, the classification results of vehicles in the target image ...