Image classification method and device, equipment and storage medium

Abstract

The embodiment of the invention discloses an image classification method and device, equipment and a storage medium, and the method comprises the steps: obtaining a to-be-classified image; determiningthe type of the to-be-classified image according to a trained target classifier, the target classifier being a classifier which is trained based on a plurality of initial classifiers and satisfies apredetermined condition; and outputting the type of the to-be-classified image.

Description

technical field [0001] The embodiments of the present application relate to computer vision, and relate to, but are not limited to, an image classification method, device, device, and storage medium. Background technique [0002] Image classification is an important problem in the field of computer vision, and with the advent of deep learning, exciting progress has been made in image classification problems. Image classification is often also a basis for other subsequent tasks. For example, when reconstructing a 3D model from an image, image classification is the basis for reconstructing a 3D model. In general, the training of classifiers requires tens of thousands of labeled samples, and the label cost of labeled samples is high. In order to reduce the labeling cost, it is of great significance to study methods of weakly supervised learning. This method can use a small number of labeled samples combined with a large number of unlabeled samples to train the classifier and ...

AI Technical Summary

Problems solved by technology

[0004] However, these methods will cause classification errors of unlabeled samples, which are difficult to correct, resulting in unsatisfactory classification results

Images