W. Ke, J. Chen, J. Jiao, G. Zhao and Q. Ye, "SRN: Side-Output Residual Network for Object Reflection Symmetry Detection and Beyond," in IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 5, pp. 1881-1895, May 2021, doi: 10.1109/TNNLS.2020.2994325
SRN : side-output residual network for object reflection symmetry detection and beyond
|Author:||Ke, Wei1; Chen, Jie2,3,4; Jiao, Jianbin5;|
1Xi’an Jiaotong University, Xi’an 710049, China
2School of Electronic and Computer Engineering, Peking University, Shenzhen 518055, China
3Peng Cheng Laboratory, Shenzhen 518055, China
4Center for Machine Vision and Signal Analysis, University of Oulu, 90014 Oulu, Finland
5School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 101408, China
|Online Access:||PDF Full Text (PDF, 5.8 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe2021102051677
Institute of Electrical and Electronics Engineers,
|Publish Date:|| 2021-10-20
This article establishes a baseline for object reflection symmetry detection in natural images by releasing a new benchmark named Sym-PASCAL and proposing an end-to-end deep learning approach for reflection symmetry. Sym-PASCAL spans challenges of multiobjects, object diversity, part invisibility, and clustered backgrounds, which is far beyond those in existing data sets. The end-to-end deep learning approach, referred to as a side-output residual network (SRN), leverages the output residual units (RUs) to fit the errors between the symmetry ground truth and the side outputs of multiple stages of a trunk network. By cascading RUs from deep to shallow, SRN exploits the “flow” of errors along multiple stages to effectively matching object symmetry at different scales and suppress the clustered backgrounds. SRN is interpreted as a boosting-like algorithm, which assembles features using RUs during network forward and backward propagations. SRN is further upgraded to a multitask SRN (MT-SRN) for joint symmetry and edge detection, demonstrating its generality to image-to-mask learning tasks. Experimental results verify that the Sym-PASCAL benchmark is challenging related to real-world images, SRN achieves state-of-the-art performance, and MT-SRN has the capability to simultaneously predict edge and symmetry mask without loss of performance.
IEEE transactions on neural networks and learning systems
|Pages:||1881 - 1895|
|Type of Publication:||
A1 Journal article – refereed
|Field of Science:||
113 Computer and information sciences
This work was supported in part by the National Natural Science Foundation of China (NSFC) under Grant 61836012, Grant 61771447, Grant 61671427, and Grant 61972217, in part by the Natural Science Foundation of Guangdong Province in China under Grant 2019B1515120049, in part by the Academy of Finland for ICT 2023 Project under Grant 328115, in part by Infotech Oulu, and in part by Business Finland.
|Academy of Finland Grant Number:||
328115 (Academy of Finland Funding decision)
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.