Open AccessLocal bi‐directional funnel network for salient object detection
Author(s) -
Pan Zefeng,
Li Junxia,
Wang Ziyang
Publication year - 2021
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
eISSN - 1350-911X
pISSN - 0013-5194
DOI - 10.1049/ell2.12021
Subject(s) - funnel , fuse (electrical) , computer science , artificial intelligence , feature (linguistics) , salient , layer (electronics) , convolution (computer science) , object (grammar) , pattern recognition (psychology) , transmission (telecommunications) , object detection , network architecture , convolutional neural network , computer vision , artificial neural network , computer network , telecommunications , engineering , mechanical engineering , linguistics , philosophy , chemistry , electrical engineering , organic chemistry
Existing deep‐learning–based saliency detection methods mainly design a sophisticated architecture to integrate multi‐level convolutional features, for example, recurrent network or bi‐directional message passing model, and achieve gratifying performance. However, the direct transmission of information with large span, for example, the information from the deepest layer and the shallowest layer, may lead to antagonistic problems. To address this problem, we propose a local bi‐directional funnel network (LBDFN) to effectively integrate multi‐level features for salient object detection. In the proposed local bi‐directional funnel network, a local bi‐directional feature integration (LBDFI) module is designed to fuse the features with similar properties from adjacent convolution layers, which can solve the problem of mismatch between fusion features well. The extensive experiments on five saliency detection datasets clearly demonstrate that the proposed method outperforms the state‐of‐the‐art approaches.