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
  • [1] A Lightweight Convolutional Neural Network for Salient Object Detection
    Fei, Fengchang
    Liu, Wei
    Shu, Lei
    TEHNICKI VJESNIK-TECHNICAL GAZETTE, 2024, 31 (04): : 1402 - 1410
  • [2] Hypergraph attentional convolutional neural network for salient object detection
    Ze-yu Liu
    Jian-wei Liu
    The Visual Computer, 2023, 39 : 2881 - 2907
  • [3] Hypergraph attentional convolutional neural network for salient object detection
    Liu, Ze-yu
    Liu, Jian-wei
    VISUAL COMPUTER, 2023, 39 (07): : 2881 - 2907
  • [4] SuperCNN: A Superpixelwise Convolutional Neural Network for Salient Object Detection
    Shengfeng He
    Rynson W. H. Lau
    Wenxi Liu
    Zhe Huang
    Qingxiong Yang
    International Journal of Computer Vision, 2015, 115 : 330 - 344
  • [5] SuperCNN: A Superpixelwise Convolutional Neural Network for Salient Object Detection
    He, Shengfeng
    Lau, Rynson W. H.
    Liu, Wenxi
    Huang, Zhe
    Yang, Qingxiong
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2015, 115 (03) : 330 - 344
  • [6] Region-based feature combination for robust salient object detection
    Vivek Kumar Singh
    Nitin Kumar
    Parma Nand
    Multimedia Tools and Applications, 2024, 83 : 35159 - 35174
  • [7] Region-based feature combination for robust salient object detection
    Singh, Vivek Kumar
    Kumar, Nitin
    Nand, Parma
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 83 (12) : 35159 - 35174
  • [8] Salient Region-Based Online Object Tracking
    Lee, Hyemin
    Kim, Daijin
    2018 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2018), 2018, : 1170 - 1177
  • [9] Salient Detection Based on Cascaded Convolutional Neural Network
    Zhang Songlong
    Xie Linbo
    LASER & OPTOELECTRONICS PROGRESS, 2019, 56 (07)
  • [10] A Fully Convolutional Network for Salient Object Detection
    Bianco, Simone
    Buzzelli, Marco
    Schettini, Raimondo
    IMAGE ANALYSIS AND PROCESSING (ICIAP 2017), PT II, 2017, 10485 : 82 - 92