Learning Efficient Representations for Image-Based Patent Retrieval

被引:1
|
作者
Wang, Hongsong [1 ]
Zhang, Yuqi [2 ]
机构
[1] Southeast Univ, Dept Comp Sci & Engn, Nanjing 210096, Peoples R China
[2] Baidu Inc, Beijing, Peoples R China
关键词
Image-Based Patent Retrieval; Patent Search; Sketch-Based Image Retrieval;
D O I
10.1007/978-981-99-8540-1_2
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Patent retrieval has been attracting tremendous interest from researchers in intellectual property and information retrieval communities in the past decades. However, most existing approaches rely on textual and metadata information of the patent, and content-based image-based patent retrieval is rarely investigated. Based on traits of patent drawing images, we present a simple and lightweight model for this task. Without bells and whistles, this approach significantly outperforms other counterparts on a large-scale benchmark and noticeably improves the state-of-the-art by 33.5% with the mean average precision (mAP) score. Further experiments reveal that this model can be elaborately scaled up to achieve a surprisingly high mAP of 93.5%. Our method ranks first in the ECCV 2022 Patent Diagram Image Retrieval Challenge.
引用
收藏
页码:15 / 26
页数:12
相关论文
共 50 条
  • [1] Learning representations for image-based profiling of perturbations
    Moshkov, Nikita
    Bornholdt, Michael
    Benoit, Santiago
    Smith, Matthew
    Mcquin, Claire
    Goodman, Allen
    Senft, Rebecca A.
    Han, Yu
    Babadi, Mehrtash
    Horvath, Peter
    Cimini, Beth A.
    Carpenter, Anne E.
    Singh, Shantanu
    Caicedo, Juan C.
    NATURE COMMUNICATIONS, 2024, 15 (01)
  • [2] Learning representations for image-based profiling of perturbations
    Nikita Moshkov
    Michael Bornholdt
    Santiago Benoit
    Matthew Smith
    Claire McQuin
    Allen Goodman
    Rebecca A. Senft
    Yu Han
    Mehrtash Babadi
    Peter Horvath
    Beth A. Cimini
    Anne E. Carpenter
    Shantanu Singh
    Juan C. Caicedo
    Nature Communications, 15
  • [3] Learning Image-based Representations for Heart Sound Classification
    Ren, Zhao
    Cummins, Nicholas
    Pandit, Vedhas
    Han, Jing
    Qian, Kun
    Schuller, Bjorn
    DH '18: PROCEEDINGS OF THE 2018 INTERNATIONAL CONFERENCE ON DIGITAL HEALTH, 2018, : 143 - 147
  • [4] Learning Transferable and Discriminative Representations for 2D Image-Based 3D Model Retrieval
    Zhou, Yaqian
    Liu, Yu
    Zhou, Heyu
    Cheng, Zhiyong
    Li, Xuanya
    Liu, An-An
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 32 (10) : 7147 - 7159
  • [5] Image Retrieval for Image-Based Localization Revisited
    Sattler, Torsten
    Weyand, Tobias
    Leibe, Bastian
    Kobbelt, Leif
    PROCEEDINGS OF THE BRITISH MACHINE VISION CONFERENCE 2012, 2012,
  • [6] Image-based form document retrieval
    Liu, JH
    Jain, AK
    FOURTEENTH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1 AND 2, 1998, : 626 - 628
  • [7] Image-based form document retrieval
    Liu, JH
    Jain, AK
    PATTERN RECOGNITION, 2000, 33 (03) : 503 - 513
  • [8] Bayesian representations and learning mechanisms for content-based image retrieval
    Vasconcelos, N
    Lippman, A
    STORAGE AND RETRIEVAL FOR MEDIA DATABASES 2000, 2000, 3972 : 43 - 54
  • [9] Learning optimal representations for image retrieval applications
    Liu, XW
    Srivastava, A
    Sun, DH
    IMAGE AND VIDEO RETRIEVAL, PROCEEDINGS, 2003, 2728 : 50 - 60
  • [10] Learning image representations for content-based image retrieval of radiotherapy treatment plans
    Huang, Charles
    Vasudevan, Varun
    Pastor-Serrano, Oscar
    Islam, Md Tauhidul
    Nomura, Yusuke
    Dubrowski, Piotr
    Wang, Jen-Yeu
    Schulz, Joseph B.
    Yang, Yong
    Xing, Lei
    PHYSICS IN MEDICINE AND BIOLOGY, 2023, 68 (09):