HEADER MODEL FOR INSTANCE SEGMENTATION, INSTANCE SEGMENTATION MODEL, IMAGE SEGMENTATION METHOD AND APPARATUS

摘要

This application discloses a header model for instance segmentation, an instance segmentation model, an image segmentation method and apparatus, and relates to the field of artificial intelligence technologies such as computer vision and deep learning technologies. The header model includes: a target box branch, including a first branch and a second branch, where the first branch is configured to process an inputted first feature map to obtain class information and confidence of a target box, and the second branch is configured to process the first feature map to obtain location information of the target box; a mask branch, configured to process an inputted second feature map to obtain mask information; the second feature map is a feature map outputted by an ROI extraction module, and the first feature map is a feature map resulting from a pooling performed on the second feature map. The application makes the segmentation information and confidence predicted by the header more accurate, resulting in a finer segmentation result of the instance segmentation.