• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

En, Qing (En, Qing.) | Duan, Lijuan (Duan, Lijuan.) (Scholars:段立娟) | Zhang, Zhaoxiang (Zhang, Zhaoxiang.) | Bai, Xiang (Bai, Xiang.) | Zhang, Yundong (Zhang, Yundong.)

Indexed by:

CPCI-S

Abstract:

We explore a principle method to address the weakly supervised detection problem. Many deep learning methods solve weakly supervised detection by mining various object proposal or pooling strategies, which may cause redundancy and generate a coarse location. To overcome this limitation, we propose a novel human-like active searching strategy that recurrently ignores the background and discovers class-specific objects by erasing undesired pixels from the image. The proposed detector acts as an agent, providing guidance to erase unremarkable regions and eventually concentrating the attention on the foreground. The proposed agents, which are composed of a deep Q-network and are trained by the Q-learning algorithm, analyze the contents of the image features to infer the localization action according to the learned policy. To the best of our knowledge, this is the first attempt to apply reinforcement learning to address weakly supervised localization with only image-level labels. Consequently, the proposed method is validated on the PASCAL VOC 2007 and PASCAL VOC 2012 datasets. The experimental results show that the proposed method is capable of locating a single object within 5 steps and has great significance to the research on weakly supervised localization with a human-like mechanism.

Keyword:

Author Community:

  • [ 1 ] [En, Qing]Beijing Univ Technol, Fac Informat Technol, Beijing Key Lab Trusted Comp, Beijing 100124, Peoples R China
  • [ 2 ] [Duan, Lijuan]Beijing Univ Technol, Fac Informat Technol, Beijing Key Lab Trusted Comp, Beijing 100124, Peoples R China
  • [ 3 ] [Zhang, Zhaoxiang]Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp, Natl Lab Pattern Reconit, Beijing 100190, Peoples R China
  • [ 4 ] [Bai, Xiang]Huazhong Univ Sci & Technol, Sch Elect Informat & Commun, Wuhan 430074, Hubei, Peoples R China
  • [ 5 ] [Zhang, Yundong]Vimicro Corp, State Key Lab Digital Multimedia Chip Technol, Beijing 100191, Peoples R China

Reprint Author's Address:

  • [Zhang, Zhaoxiang]Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp, Natl Lab Pattern Reconit, Beijing 100190, Peoples R China

Show more details

Related Keywords:

Related Article:

Source :

NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE

ISSN: 2159-5399

Year: 2019

Page: 3502-3509

Language: English

Cited Count:

WoS CC Cited Count: 1

SCOPUS Cited Count:

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 2

Affiliated Colleges:

Online/Total:689/5315780
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.