公开(公告)号：US12130887B2

公开(公告)日：2024-10-29

申请号：US17515180

申请日：2021-10-29

Applicant: Tencent Technology (Shenzhen) Company Limited

Inventor： Peng Sun ,  Jiaxiang Wu

IPC: G06K9/62 ,  G06F18/21 ,  G06F18/214 ,  G06F18/25 ,  G06N3/04 ,  G06N3/082 ,  G06T7/70 ,  G06V10/26 ,  G06V10/70 ,  G06V10/80 ,  G06V10/82 ,  G06V20/40 ,  G06V20/70

CPC classification number: G06F18/214 ,  G06F18/217 ,  G06F18/253 ,  G06N3/04 ,  G06N3/082 ,  G06T7/70 ,  G06V10/267 ,  G06V10/70 ,  G06V10/806 ,  G06V10/82 ,  G06V20/41 ,  G06V20/70 ,  G06T2207/20084

Abstract: This application provides a semantic segmentation network structure generation method performed by an electronic device, and a non-transitory computer-readable storage medium. The method includes: generating a corresponding architectural parameter for cells that form a super cell in a semantic segmentation network structure; optimizing the semantic segmentation network structure based on image samples, and removing a redundant cell from a super cell to which a target cell pertains, to obtain an improved semantic segmentation network structure; performing, by an aggregation cell in the improved semantic segmentation network structure, feature fusion on an output of the super cell; performing recognition processing on a fused feature map, to determine positions corresponding to objects that are in the image samples; and training the improved semantic segmentation network structure based on the positions corresponding to the objects that are in the image samples and annotations corresponding to the image samples, to obtain a trained semantic segmentation network structure.