Advertisement

Weakly Supervised Deep Learning for Objects Detection from Images

  • Jianfang Shi
  • Xiaohui YuanEmail author
  • Mohamed Elhoseny
  • Xiaojing Yuan
Conference paper
  • 30 Downloads
Part of the Studies in Distributed Intelligence book series (SDI)

Abstract

Training of a convolutional neural network for object detection requires a large number of images with pixel-level annotations. Weakly supervised learning uses image-level labels to circumvent the issue of lack of semantic examples, which remains an open challenging. This paper proposes a cascaded deep network architecture that leverages the class activation mapping with global average pooling. The first stage of this architecture learns to infer object localization maps based on the image-level annotations, which generates bounding boxes of objects in every image. These image patches are adhesion areas in the original image. In the second stage, the image patches are used to train the detection network. Experiments are conducted using the PASCAL VOC 2012 datasets. Our proposed method obtains a mean average precision of 87.2% and demonstrates a competitive performance of classification performance with respect to the state-of-the-art methods. In the evaluation of object localization, the recall of our method is improved by 9%.

Keywords

Weakly supervised learning Neural networks Deep learning Object detection 

References

  1. 1.
    B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, A. Torralba, Learning deep features for discriminative localization. in Computer Vision and Pattern Recognition, 2016Google Scholar
  2. 2.
    G. Papandreou, L.C. Chen, K. Murphy, A.L. Yuille, Weakly-and semi-supervised learning of a CNN for semantic image segmentation. in International Conference on Computer Vision, 2015Google Scholar
  3. 3.
    A. Chaudhry, P.K. Dokania, P.H.S. Torr, Discovering class-specific pixels for weakly supervised semantic segmentation. in Computer Vision and Pattern Recognition, 2017Google Scholar
  4. 4.
    N. Liu, J. Han, DHSNet: deep hierarchical saliency network for salient object detection. in IEEE Conference on Computer Vision and Pattern Recognition, pp. 678–686, 2016Google Scholar
  5. 5.
    A. Kolesnikov, C.H. Lampert, Seed expand and constrain: three principles for weakly-supervised. In European Conference on Computer Vision, pp. 695–711, 2016Google Scholar
  6. 6.
    H. Zhang, Z. Kyaw, J. Yu, S.F. Chang, PPR-FCN: weakly supervised visual relation detection via parallel pairwise R-FCN. in IEEE International Conference on Computer Vision, pp. 4243–4251, 2017Google Scholar
  7. 7.
    K. He, X. Zhang, S. Ren, J. Sun, Spatial pyramid pooling in deep convolutional networks for visual recognition. In European Conference on Computer Vision, pp. 346–361, 2014Google Scholar
  8. 8.
    M. Tang, A. Djelouah, F. Perazzi, Y. Boykov, C. Schroers, Normalized cut loss for weakly supervised CNN segment. in Computer Vision and Pattern Recognition, 2018Google Scholar
  9. 9.
    J. Long, E. Shelhamer, T. Darrell. Fully convolutional networks for semantic segmentation. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440, 2015Google Scholar
  10. 10.
    J. Dai, K. He, J. Sun, BoxSup: exploiting bounding boxes to supervise convolutional networks for semantic segmentation. in IEEE International Conference on Computer Vision, pp. 1635–1643, 2015Google Scholar
  11. 11.
    P.O. Pinheiro, R. Collobert. Weakly supervised semantic segmentation with convolutional networks. in Computer Vision and Pattern Recognition, 2015Google Scholar
  12. 12.
    D. Lin, J. Dai, J. Jia, K. He, J. Sun, ScribbleSup: scribble-supervised convolutional networks for semantic segmentation. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3159–3167, 2016Google Scholar
  13. 13.
    N. Krishnaraj, M. Elhoseny, M. Thenmozhi, M.M. Selim, K. Shankar, Deep learning model for real-time image compression in Internet of Underwater Things (IoUT). J. Real-Time Image Process. 2019.  https://doi.org/10.1007/s11554-019-00879-6
  14. 14.
    M. Elhoseny, G.-B. Bian, S.K. Lakshmanaprabu, K. Shankar, A.K. Singh, W. Wu, Effective features to classify ovarian cancer data in internet of medical things. Comput. Netw. 159, 147–156 (2019)CrossRefGoogle Scholar
  15. 15.
    B.S. Murugan, M. Elhoseny, K. Shankar, J. Uthayakumar, Region-based scalable smart system for anomaly detection in pedestrian walkways. Comput. Electr. Eng. 75, 146–160 (2019)CrossRefGoogle Scholar
  16. 16.
    K. Shankar, M. Elhoseny, S.K. Lakshmanaprabu, M. Ilayaraja, R.M. Vidhyavathi, M. Alkhambashi, Optimal feature level fusion based ANFIS classifier for brain MRI image classification. Concurrency Comput. Pract. Exp. 2018.  https://doi.org/10.1002/cpe.4887
  17. 17.
    X. Yuan, D. Li, D. Mohapatra, M. Elhoseny, Automatic removal of complex shadows from indoor videos using transfer learning and dynamic thresholding. Comput. Electr. Eng. 70, 813–825 (2018)CrossRefGoogle Scholar
  18. 18.
    P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus, Y. LeCun, OverFeat: integrated recognition, localization and detection using convolutional networks. in IEEE Conference on Computer Vision and Pattern Recognition, 2013Google Scholar
  19. 19.
    T. Durand, T. Mordan, N. Thome, M. Cord, WILDCAT: weakly supervised learning of deep ConvNets for image classification, pointwise localization, and segmentation. in IEEE Conference on Computer Vision and Pattern Recognition, pp. 5957–5966, 2017Google Scholar
  20. 20.
    Y. Wei, X. Liang, Y. Chen, X. Shen, M.-M. Cheng, J. Feng, Y. Zhao, S. Yan, STC: a simple to complex framework for weakly supervised semantic segmentation. in IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016Google Scholar
  21. 21.
    Y. Wei, J. Feng, X. Liang, M.M. Cheng, Y. Zhao, S. Yan, Object region mining with adversarial erasing: a simple classification to semantic segmentation approach. in Conference on Computer Vision and Pattern Recognition, 2017Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Jianfang Shi
    • 1
  • Xiaohui Yuan
    • 2
    Email author
  • Mohamed Elhoseny
    • 3
  • Xiaojing Yuan
    • 4
  1. 1.College of Information and Computer, Taiyuan University of TechnologyTaiyuanChina
  2. 2.Department of Computer Scienceand Engineering, University of North TexasDentonUSA
  3. 3.Faculty of Computers and Information, Mansoura UniversityMansouraEgypt
  4. 4.University of HoustonHoustonUSA

Personalised recommendations