Masking Salient Object Detection, a Mask Region-based Convolutional Neural Network Analysis for Segmentation of Salient Objects

被引:2
|
作者
Krinski, Bruno A. [1 ]
Ruiz, Daniel, V [1 ]
Machado, Guilherme Z. [1 ]
Todt, Eduardo [1 ]
机构
[1] Fed Univ Parana UFPR, Dept Informat, Curitiba, Parana, Brazil
关键词
VISUAL-ATTENTION; MODEL;
D O I
10.1109/LARS-SBR-WRE48964.2019.00018
中图分类号
TP24 [机器人技术];
学科分类号
080202 ; 1405 ;
摘要
In this paper, we propose a broad comparison between Fully Convolutional Networks (FCNs) and Mask Region-based Convolutional Neural Networks (Mask-RCNNs) applied in the Salient Object Detection (SOD) context. Studies in the SOD literature usually explore architectures based in FCNs to detect salient regions and objects in visual scenes. However, besides the promising results achieved, FCNs showed issues in some challenging scenarios. Fairly recently studies in the SOD literature proposed the use of a Mask-RCNN approach to overcome such issues. However, there is no extensive comparison between the two networks in the SOD literature endorsing the effectiveness of Mask-RCNNs over FCN when segmenting salient objects. Aiming to effectively show the superiority of Mask-RCNNs over FCNs in the SOD context, we compare two variations of Mask-RCNNs with two variations of FCNs in eight datasets widely used in the literature and in four metrics. Our findings show that in this context Mask-RCNNs achieved an improvement on the F-measure up to 47% over FCNs.
引用
下载
收藏
页码:55 / 60
页数:6
相关论文
共 50 条
  • [41] Region-based scalable self-recovery for salient-object images
    Daneshmandpour, Navid
    Danyali, Habibollah
    Helfroush, Mohammad Sadegh
    ETRI JOURNAL, 2021, 43 (01) : 109 - 119
  • [42] Coconut trees detection and segmentation in aerial imagery using mask region-based convolution neural network
    Iqbal, Muhammad Shakaib
    Ali, Hazrat
    Tran, Son N.
    Iqbal, Talha
    IET COMPUTER VISION, 2021, 15 (06) : 428 - 439
  • [43] Salient Object Detection Using Cascaded Convolutional Neural Networks and Adversarial Learning
    Tang, Youbao
    Wu, Xiangqian
    IEEE TRANSACTIONS ON MULTIMEDIA, 2019, 21 (09) : 2237 - 2247
  • [44] A Shape Preserving Approach for Salient Object Detection Using Convolutional Neural Networks
    Kim, Jongpil
    Pavlovic, Vladimir
    2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2016, : 609 - 614
  • [45] Region Fusion and Grab-cut Based Salient Object Segmentation
    Wang Hailuo
    Wang Bo
    Zhou Zhiqiang
    Song Lu
    Li Sun
    Wu Shujie
    2014 SIXTH INTERNATIONAL CONFERENCE ON INTELLIGENT HUMAN-MACHINE SYSTEMS AND CYBERNETICS (IHMSC), VOL 1, 2014, : 131 - 135
  • [46] Structure extraction and region contrast based salient object detection
    Zhang, Qing
    Lin, Jiajun
    Xie, Zhigang
    EIGHTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2016), 2016, 10033
  • [47] SRFCNM: Spatiotemporal recurrent fully convolutional network model for salient object detection
    Ishita Arora
    M. Gangadharappa
    Multimedia Tools and Applications, 2024, 83 : 38009 - 38036
  • [48] Salient Object Detection with Chained Multi-Scale Fully Convolutional Network
    Tang, Youbao
    Wu, Xiangqian
    PROCEEDINGS OF THE 2017 ACM MULTIMEDIA CONFERENCE (MM'17), 2017, : 618 - 626
  • [49] MULTI-SCALE GRAPH CONVOLUTIONAL INTERACTION NETWORK FOR SALIENT OBJECT DETECTION
    Che, Wenqi
    Sun, Luoyi
    Xie, Zhifeng
    Ding, Youdong
    Han, Kaili
    2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2021, : 679 - 683
  • [50] JointRCNN: A Region-Based Convolutional Neural Network for Optic Disc and Cup Segmentation
    Jiang, Yuming
    Duan, Lixin
    Cheng, Jun
    Gu, Zaiwang
    Xia, Hu
    Fu, Huazhu
    Li, Changsheng
    Liu, Jiang
    IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2020, 67 (02) : 335 - 343