Exploring ubiquitous relations for boosting classification and localization

被引：0
|
作者：
Sun, Xin [1 ]
Chen, Changrui [1 ]
Dong, Junyu [1 ]
Liu, Dan [1 ]
Hu, Guosheng [2 ]
机构：
[1] Department of Computer Science and Technology, Ocean University of China, China
[2] School of Electronics Electrical Engineering and Computer Science, Queen's University Belfast, United Kingdom
来源：
Knowledge-Based Systems | 2021年 / 196卷
关键词：
Although the weakly supervised learning can effectively avoid the tedious data annotating process of deep learning approaches; the performance is still in urgent need of enhancement. In this paper; we endeavor to mine a ubiquitous and fundamental knowledge—Relation; to boost several existing classification and localization models without changing the original structure. We first propose a universal relation exploring scheme to mine the relations among entities. This scheme can be specialized into different instantiations including object; superpixel and pixel relations to stimulating different learning models. We adopt the object relations on a few-shot classification model to concentrate on the dominant object; and to boost its discriminative capacity. The superpixel relation is utilized to improve the performance of the saliency object detection models. The sensitivity of the pixel relations to the uncertain regions makes it suitable for distinguishing the disputed area in saliency detection results. Our experiments demonstrate that all the three relation instantiations can significantly boost the performance of the state-of-the-art learning models and optimize the visual result. © 2020 Elsevier B.V;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
引用
收藏
相关论文
共 50 条
  • [21] Interactive boosting for image classification
    Lu, Yijuan
    Tian, Qi
    Huan, Thomas S.
    MULTIMEDIA CONTENT ANALYSIS AND MINING, PROCEEDINGS, 2007, 4577 : 315 - +
  • [22] Minimum majority classification and boosting
    Long, PM
    EIGHTEENTH NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE (AAAI-02)/FOURTEENTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE (IAAI-02), PROCEEDINGS, 2002, : 181 - 186
  • [23] Individualized boosting learning for classification
    Fan, Zizhu
    Ni, Ming
    OPTIK, 2015, 126 (24): : 5733 - 5739
  • [24] Boosting image classification scheme
    Qiu, XP
    Feng, Z
    Wu, LD
    2004 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXP (ICME), VOLS 1-3, 2004, : 1271 - 1274
  • [25] Bagging, boosting and ordinal classification
    Hechenbichler, K
    Tutz, G
    Classification - the Ubiquitous Challenge, 2005, : 145 - 152
  • [26] Interactive boosting for image classification
    Lu, Yijuan
    Tian, Qi
    Huang, Thomas S.
    MULTIPLE CLASSIFIER SYSTEMS, PROCEEDINGS, 2007, 4472 : 180 - +
  • [27] Boosting SpLSA for Text Classification
    Hurtado, Julio
    Mendoza, Marcelo
    Nanculef, Ricardo
    PROGRESS IN PATTERN RECOGNITION, IMAGE ANALYSIS, COMPUTER VISION, AND APPLICATIONS, CIARP 2016, 2017, 10125 : 142 - 149
  • [28] Boosting for graph classification with universum
    Pan, Shirui
    Wu, Jia
    Zhu, Xingquan
    Long, Guodong
    Zhang, Chengqi
    KNOWLEDGE AND INFORMATION SYSTEMS, 2017, 50 (01) : 53 - 77
  • [29] Design of a process for localization system in ubiquitous space
    Yamauchi., T.
    Iwatake, Toru
    INTERNATIONAL JOURNAL OF INTERACTIVE DESIGN AND MANUFACTURING - IJIDEM, 2008, 2 (04): : 183 - 193
  • [30] Localization of ubiquitous environment based mobile robot
    Kim, Yong-Shik
    Lee, Jae Hoon
    Kim, Bong Keun
    Do, Hyunmin
    Tomizawa, Tetsuo
    2007 INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND SYSTEMS, VOLS 1-6, 2007, : 1194 - 1197
12345