A High Resolution Semantic Segmentation Method via Multi-Branch Structure and Gating Mechanism
In order to solve the problem that HRNetv2 and other multi-branch structure networks cannot ef-fectively fuse multi-level features in semantic segmentation tasks,a new multi-level feature fusion method based on the gating mechanism is proposed.Firstly,a gated fusion unit is constructed to fuse the feature in-formation of multiple branches selectively.Secondly,a bottom-up fusion method is adopted to progressively enhance the feature representation of each branch by means of spreading semantically high-level features and detailed low-level features.Finally,features of branches are concatenated channel-wisely to output the predicted mask,and the bilinear interpolation algorithm is used to restore the original image size.Experi-ments show that the proposed method with only a few parameters achieves 77.01％mIoU and 80.43％mIoU in PASCAL VOC 2012+Aug and Cityscapes respectively,increases by 1.14 percentage points and 1.92 per-centage points compared with HRNetv2-W48,and outperforms many baseline models.
万方数据
维普
