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
  • [41] Approaching information infrastructure as an ecology of ubiquitous sociotechnical relations
    Constantinides, P
    Barrett, M
    Designing Ubiquitous Information Environments: Socio-Technical Issues and Challenges, 2005, 185 : 249 - 260
  • [42] Privacy Preserving in Ubiquitous Computing: Classification & Hierarchy
    Ma, Tinghuai
    Yan, Sen
    Wang, Jin
    Lee, Sungyoung
    COMPUTER SCIENCE AND INFORMATION SYSTEMS, 2011, 8 (04) : 1185 - 1206
  • [43] Genetic Boosting Classification for Malware Detection
    Martin, Alejandro
    Menendez, Hector D.
    Camacho, David
    2016 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), 2016, : 1030 - 1037
  • [44] Feature Boosting in Natural Image Classification
    Saxena, Piyush
    Saxena, Devansh
    Nie, Xiao
    Helmers, Aaron
    Ramachandran, Nithin
    Sakib, Nazmus
    Ahamed, Sheikh
    2019 IEEE 43RD ANNUAL COMPUTER SOFTWARE AND APPLICATIONS CONFERENCE (COMPSAC), VOL 2, 2019, : 61 - 67
  • [45] LDA boost classification: boosting by topics
    La Lei
    Guo Qiao
    Cao Qimin
    Li Qitao
    EURASIP Journal on Advances in Signal Processing, 2012
  • [46] Selection of binary variables and classification by boosting
    Park, Junyong
    Wilbur, Jayson D.
    Ghosh, Jayanta K.
    Nakatsu, Cindy H.
    Ackerman, Corinne
    COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION, 2007, 36 (04) : 855 - 869
  • [47] Gradient and Newton boosting for classification and regression
    Sigrist, Fabio
    EXPERT SYSTEMS WITH APPLICATIONS, 2021, 167
  • [48] An efficient version of inverse boosting for classification
    Gao, Jingyang
    Chen, Chenglizhao
    Zhen, Dantong
    Zhu, Qunxiong
    TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL, 2013, 35 (02) : 188 - 199
  • [49] Using boosting to simplify classification models
    Wheway, V
    2001 IEEE INTERNATIONAL CONFERENCE ON DATA MINING, PROCEEDINGS, 2001, : 558 - 565
  • [50] Collaborative Boosting for Activity Classification in Microblogs
    Song, Yangqiu
    Lu, Zhengdong
    Leung, Cane Wing-ki
    Yang, Qiang
    19TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING (KDD'13), 2013, : 482 - 490
12345