Image segmentation method and device, computer equipment and storage medium

The invention relates to the technical field of computers, in particular to an image segmentation method and device, computer equipment and a storage medium. The method comprises the steps of obtaining a to-be-segmented image, wherein the to-be-segmented image comprises a plurality of different types of objects; extracting initial features of the to-be-segmented image to obtain an initial featuremap; extracting object internal feature information and inter-object feature information corresponding to each object from the initial feature map; and obtaining a segmentation result corresponding toeach object according to the object internal feature information, the inter-object feature information and the initial feature map. The method can improve the accuracy of image segmentation. 本申请涉及计算机技术领域，特别是涉及一种图像分割方法、装置、计算机设备和存储介质。所述方法包括：获取待分割图像，待分割图像包括多个不同类别的对象；对待分割图像进行初始特征的提取，得到初始特征图；从初始特征图中提取出对应各对象的对象内部特征信息和对象间特征信息；根据对象内部特征信息、对象间特征信息以及初始特征图，得到对应各对象的分割结果。采用本方法能够提升图像分割的准确性。