Weakly Supervised Object Localization Based on Attention Mechanism and Categorical Hierarchy

被引：0
|
作者：
Feng X. [1 ,2 ,3 ]
Yang J. [1 ,2 ,3 ]
Zhou T. [1 ,2 ,3 ]
Gong C. [1 ,2 ,3 ]
机构：
[1] Pattern Computing and Application Laboratory, School of Computer Science and Engineering, Nanjing University of Science &Technology, Nanjing
[2] Key Laboratory of Intelligent Perception and Systems for High-dimensional Information, Ministry of Education, Nanjing University of Science & Technology, Nanjing
[3] Key Laboratory of Image and Video Understanding for Social Security of Jiangsu Province, Nanjing University of Science & Technology, Nanjing
来源：
Ruan Jian Xue Bao/Journal of Software | 2023年 / 34卷 / 10期
关键词：
background interference; convolutional neural network (CNN); hierarchical network; network attention; weakly supervised object localization;
D O I：
10.13328/j.cnki.jos.006675
中图分类号：
学科分类号：
摘要：
Weakly supervised object localization aims to train target locators only by image-level labels instead of accurate location annotations for algorithm training. Some existing methods can only identify the most discriminative region of the target object and are incapable of covering the complete object, or can easily be misled by irrelevant background information, thereby leading to inaccurate object locations. Therefore, this study proposes a weakly supervised object localization algorithm based on attention mechanism and categorical hierarchy. The proposed method extracts a more complete object area by performing mean segmentation on the attention map of the convolutional neural network. In addition, the category hierarchy network is utilized to weaken the attention caused by background areas, which achieves more accurate object location results. Extensive experimental results on multiple public datasets show that the proposed method can yield better localization effects than other weakly supervised object localization methods under various evaluation metrics. © 2023 Chinese Academy of Sciences. All rights reserved.
引用
收藏
页码：4916 / 4929
页数：13
相关论文
共 33 条
  • [1] Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, LeCun Y., OverFeat: Integrated recognition, localization and detection using convolutional networks, (2014)
  • [2] Redmon J, Divvala S, Girshick R, Farhadi A., You only look once: Unified, real-time object detection, Proc. of the 2016 IEEE Conf. on Computer Vision and Pattern Recognition, pp. 779-788, (2016)
  • [3] Ren SQ, He KM, Girshick B, Sun J., Faster R-CNN: Towards real-time object detection with region proposal networks, IEEE Trans. on Pattern Analysis and Machine Intelligence, 39, 6, pp. 1137-1149, (2017)
  • [4] Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC., SSD: Single shot multibox detector, Proc. of the 14th European Conf. on Computer Vision, pp. 21-37, (2016)
  • [5] Pei W, Xu YM, Zhu YY, Wang PQ, Lu MY, Li F., The target detection method of aerial photography images with improved SSD, Ruan Jian Xue Bao/Journal of Software, 30, 3, (2019)
  • [6] Zhou BL, Khosla A, Lapedriza A, Oliva A, Torralba A., Learning deep features for discriminative localization, Proc. of the 2016 IEEE Conf. on Computer Vision and Pattern Recognition, pp. 2921-2929, (2016)
  • [7] Li Y, Liu Y, Liu GJ, Guo MZ., Weakly supervised image semantic segmentation method based on object location cues, Ruan Jian Xue Bao/Journal of Software, 31, 11, pp. 3640-3656, (2020)
  • [8] Singh KK, Lee YJ., Hide-and-Seek: Forcing a network to be meticulous for weakly-supervised object and action localization, Proc. of the 2017 IEEE Int’l Conf. on Computer Vision, pp. 3544-3553, (2017)
  • [9] Yun SD, Han D, Chun S, Oh SJ, Yoo Y, Choe J., CutMix: Regularization strategy to train strong classifiers with localizable features, Proc. of the 2019 IEEE/CVF Int’l Conf. on Computer Vision, pp. 6022-6031, (2019)
  • [10] Zhang XL, Wei YC, Feng JS, Yang Y, Huang T., Adversarial complementary learning for weakly supervised object localization, Proc. of the 2018 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, pp. 1325-1334, (2018)
1234