Image classification method and device, electronic equipment and storage medium

The invention discloses an image classification method and device, electronic equipment and a storage medium, is applied to the field of artificial intelligence, and particularly relates to a computer vision and deep learning technology. The specific implementation scheme of the image classification method comprises the steps of extracting features of a to-be-classified image to obtain multiple pieces of feature data; clustering the plurality of feature data to obtain a clustering result; performing weighting processing on the multiple pieces of feature data based on the clustering result to obtain multiple pieces of weighted feature data; and classifying the to-be-classified image based on the plurality of weighted feature data to obtain the category of the to-be-classified image in the at least two predetermined categories. 本公开公开了一种图像分类方法、装置、电子设备和存储介质，应用于人工智能领域，具体涉及计算机视觉和深度学习技术。图像分类方法的具体实现方案为：提取待分类图像的特征，得到多个特征数据；对多个特征数据进行聚类，得到聚类结果；基于聚类结果对多个特征数据进行加权处理，得到多个加权后特征数据；以及基于多个加权后特征数据对待分类图像进行分类，得到至少两个预定类别中待分类图像的类别。