Salient region detection is a fundamental problem in computer vision and image processing. Deep learning models perform better than traditional approaches but suffer from their huge parameters and slow speeds. To handle these problems, in this paper we propose the multi-feature fusion network (MFFN) - a efficient salient region detection architecture based on Convolution Neural Network (CNN). A novel feature extraction structure is designed to obtain feature maps from CNN. A fusion dense block is used to fuse all low-level and high-level feature maps to derive salient region results. MFFN is an end-to-end architecture which does not need any post-processing procedures. Experiments on the benchmark datasets demonstrate that MFFN achieves the state-of-the-art performance on salient region detection and requires much less parameters and computation time. Ablation experiments demonstrate the effectiveness of each module in MFFN.
Zheng FANG
Army Engineering University
Tieyong CAO
Army Engineering University
Jibin YANG
Army Engineering University
Meng SUN
Army Engineering University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Zheng FANG, Tieyong CAO, Jibin YANG, Meng SUN, "Multi-Feature Fusion Network for Salient Region Detection" in IEICE TRANSACTIONS on Fundamentals,
vol. E102-A, no. 6, pp. 834-841, June 2019, doi: 10.1587/transfun.E102.A.834.
Abstract: Salient region detection is a fundamental problem in computer vision and image processing. Deep learning models perform better than traditional approaches but suffer from their huge parameters and slow speeds. To handle these problems, in this paper we propose the multi-feature fusion network (MFFN) - a efficient salient region detection architecture based on Convolution Neural Network (CNN). A novel feature extraction structure is designed to obtain feature maps from CNN. A fusion dense block is used to fuse all low-level and high-level feature maps to derive salient region results. MFFN is an end-to-end architecture which does not need any post-processing procedures. Experiments on the benchmark datasets demonstrate that MFFN achieves the state-of-the-art performance on salient region detection and requires much less parameters and computation time. Ablation experiments demonstrate the effectiveness of each module in MFFN.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E102.A.834/_p
Copy
@ARTICLE{e102-a_6_834,
author={Zheng FANG, Tieyong CAO, Jibin YANG, Meng SUN, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Multi-Feature Fusion Network for Salient Region Detection},
year={2019},
volume={E102-A},
number={6},
pages={834-841},
abstract={Salient region detection is a fundamental problem in computer vision and image processing. Deep learning models perform better than traditional approaches but suffer from their huge parameters and slow speeds. To handle these problems, in this paper we propose the multi-feature fusion network (MFFN) - a efficient salient region detection architecture based on Convolution Neural Network (CNN). A novel feature extraction structure is designed to obtain feature maps from CNN. A fusion dense block is used to fuse all low-level and high-level feature maps to derive salient region results. MFFN is an end-to-end architecture which does not need any post-processing procedures. Experiments on the benchmark datasets demonstrate that MFFN achieves the state-of-the-art performance on salient region detection and requires much less parameters and computation time. Ablation experiments demonstrate the effectiveness of each module in MFFN.},
keywords={},
doi={10.1587/transfun.E102.A.834},
ISSN={1745-1337},
month={June},}
Copy
TY - JOUR
TI - Multi-Feature Fusion Network for Salient Region Detection
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 834
EP - 841
AU - Zheng FANG
AU - Tieyong CAO
AU - Jibin YANG
AU - Meng SUN
PY - 2019
DO - 10.1587/transfun.E102.A.834
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E102-A
IS - 6
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - June 2019
AB - Salient region detection is a fundamental problem in computer vision and image processing. Deep learning models perform better than traditional approaches but suffer from their huge parameters and slow speeds. To handle these problems, in this paper we propose the multi-feature fusion network (MFFN) - a efficient salient region detection architecture based on Convolution Neural Network (CNN). A novel feature extraction structure is designed to obtain feature maps from CNN. A fusion dense block is used to fuse all low-level and high-level feature maps to derive salient region results. MFFN is an end-to-end architecture which does not need any post-processing procedures. Experiments on the benchmark datasets demonstrate that MFFN achieves the state-of-the-art performance on salient region detection and requires much less parameters and computation time. Ablation experiments demonstrate the effectiveness of each module in MFFN.
ER -