Method and apparatus for predicting multi-label categories of images, electronic device, and storage medium

Abstract

The present disclosure relates to a method and apparatus for predicting multi-label categories of images, an electronic device and a storage medium, the method comprising: performing feature extraction according to distillation features of an image to be predicted to obtain distillation feature information of the image to be predicted, wherein the distillation features comprising features obtainedafter knowledge distillation from a weak supervisory detection model used for class detection of the image; performing classification prediction processing on the distillation feature information toobtain the classification prediction confidence of the image to be predicted; determining the class prediction result of the image to be predicted according to the class prediction confidence of the image to be predicted. Embodiments of the present disclosure can realize distillation at a feature level, and can extract features from an image to be predicted using distillation features obtained after knowledge distillation from a weakly supervised detection model, so that a class prediction process of an image to be predicted is more efficient and a class prediction result is more accurate.

Description

technical field [0001] The present disclosure relates to the technical field of image processing, and in particular to an image multi-label category prediction method and device, electronic equipment, and a storage medium. Background technique [0002] When performing multi-label category prediction on images, the model can be used to make predictions. Since the multi-label image itself contains diverse semantic information, multiple categories are required for description, and the number of categories is uncertain, so the model needs to have a deep understanding of the image. And there are correlations between categories, and the correlation between categories has a significant impact on the prediction results, but the correlation between categories is difficult to carry out adaptive modeling, leading to the traditional use of models to predict multi-label categories of images method, the model lacks adaptability and the model is highly complex, and it is necessary to manu...

AI Technical Summary

Problems solved by technology

And there are correlations between categories, and the correlation between categories has a significant impact on the prediction results, but the correlation between categories is difficult to carry out adaptive modeling, leading to the traditional use of models to predict multi-label categories of images method, the model lacks adaptability and the model is highly complex, and it is necessary to manually pre-define the relationship between the label categories of the image

Images