Premium
Deep boundary‐aware semantic image segmentation
Author(s) -
Wu Huisi,
Li Yifan,
Chen Le,
Liu Xueting,
Li Ping
Publication year - 2021
Publication title -
computer animation and virtual worlds
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.225
H-Index - 49
eISSN - 1546-427X
pISSN - 1546-4261
DOI - 10.1002/cav.2023
Subject(s) - computer science , pyramid (geometry) , segmentation , artificial intelligence , fuse (electrical) , context (archaeology) , boundary (topology) , convolutional neural network , pooling , pattern recognition (psychology) , feature (linguistics) , image segmentation , image (mathematics) , computer vision , mathematics , paleontology , mathematical analysis , linguistics , philosophy , geometry , electrical engineering , biology , engineering
Abstract While extensive research efforts have been made in semantic image segmentation, the state‐of‐the‐art methods still suffer from blurry boundaries and mismatched objects due to the insufficient multiscale adaptability. In this paper, we propose a two‐branch convolutional neural network (CNN) approach to capture the multiscale context and the boundary information with the two branches, respectively. To capture the multiscale context, we propose to embed self‐attention mechanism to the atrous spatial pyramid pooling network. To capture the boundary information, we propose to fuse the low‐level features in boundary feature extraction for refining the extracted boundaries via a feature fusion layer (FFL). With FFL, our method can improve the segmentation result with clearer boundaries. A new loss function is proposed which contains a segmentation loss and a boundary loss. Experiments show that our method can predict the boundaries of objects more clearly and have better performance for small‐scale objects.