Deep boundary-aware semantic image segmentation

Huisi Wu, Yifan Li, Le Chen, Xueting Liu, Ping Li

Research output: Journal article publicationJournal articleAcademic researchpeer-review

1 Citation (Scopus)


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.

Original languageEnglish
Article numbere2023
Pages (from-to)1-12
JournalComputer Animation and Virtual Worlds
Issue number3-4
Publication statusPublished - Jul 2021


  • boundary-aware mechanism
  • semantic segmentation
  • two-branch CNN

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'Deep boundary-aware semantic image segmentation'. Together they form a unique fingerprint.

Cite this