single-jc.php

JACIII Vol.27 No.5 pp. 886-895
doi: 10.20965/jaciii.2023.p0886
(2023)

Research Paper:

An Object Detection Method Using Probability Maps for Instance Segmentation to Mask Background

Shinji Uchinoura, Junichi Miyao, and Takio Kurita

Hiroshima University
1-4-1 Kagamiyama, Higashi-Hiroshima-shi, Hiroshima 739-8527, Japan

Received:
February 23, 2023
Accepted:
May 15, 2023
Published:
September 20, 2023
Keywords:
object detection, instance segmentation, deep neural networks
Abstract

This paper proposes a two-step detector called segmented object detection, whose performance is improved by masking the background region. Previous single-stage object detection methods suffer from the problem of imbalance between foreground and background classes, where the background occupies more regions in the image than the foreground. Thus, the loss from the background is firmly incorporated into the training. RetinaNet addresses this problem with Focal Loss, which focuses on foreground loss. Therefore, we propose a method that generates probability maps using instance segmentation in the first step and feeds back the generated maps as background masks in the second step as prior knowledge to reduce the influence of the background and enhance foreground training. We confirm that the detector can improve the accuracy by adding instance segmentation information to both the input and output rather than only to the output results. On the Cityscapes dataset, our method outperforms the state-of-the-art methods.

Overview of the proposed method

Overview of the proposed method

Cite this article as:
S. Uchinoura, J. Miyao, and T. Kurita, “An Object Detection Method Using Probability Maps for Instance Segmentation to Mask Background,” J. Adv. Comput. Intell. Intell. Inform., Vol.27 No.5, pp. 886-895, 2023.
Data files:
References
  1. [1] S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards real-time object detection with region proposal networks,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.39, No.6, pp. 1137-1149, 2016. https://doi.org/10.1109/TPAMI.2016.2577031
  2. [2] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” Proc. of 2016 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 779-788, 2016. https://doi.org/10.1109/CVPR.2016.91
  3. [3] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg, “SSD: Single shot multibox detector,” European Conf. on Computer Vision (ECCV2016), pp. 21-37, 2016. https://doi.org/10.1007/978-3-319-46448-0_2
  4. [4] R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” Proc. of 2014 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 580-587, 2014. https://doi.org/10.1109/CVPR.2014.81
  5. [5] R. Girshick, “Fast R-CNN,” Proc. of 2015 IEEE Int. Conf. on Computer Vision (ICCV), pp. 1440-1448, 2015. https://doi.org/10.1109/ICCV.2015.169
  6. [6] Z. Cai and N. Vasconcelos, “Cascade R-CNN: Delving into high quality object detection,” Proc. of 2018 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 6154-6162, 2018. https://doi.org/10.1109/CVPR.2018.00644
  7. [7] T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal loss for dense object detection,” Proc. of 2017 IEEE Int. Conf. on Computer Vision (ICCV), pp. 2999-3007, 2017. https://doi.org/10.1109/ICCV.2017.324
  8. [8] Z. Tian, C. Shen, H. Chen, and T. He, “Fcos: Fully convolutional one-stage object detection,” Proc. of 2019 IEEE/CVF Int. Conf. on Computer Vision (ICCV), pp. 9626-9635, 2019. https://doi.org/10.1109/ICCV.2019.00972
  9. [9] X. Wang, T. Kong, C. Shen, Y. Jiang, and L. Li, “Solo: Segmenting objects by locations,” European Conf. on Computer Vision (ECCV2020), pp. 649-665, 2020. https://doi.org/10.1007/978-3-030-58523-5_38
  10. [10] Z. Tian, C. Shen, and H. Chen, “Conditional convolutions for instance segmentation,” European Conf. on Computer Vision (ECCV2020), pp. 282-298, 2020. https://doi.org/10.1007/978-3-030-58452-8_17
  11. [11] J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semantic segmentation,” Proc. of 2015 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 3431-3440, 2015. https://doi.org/10.1109/CVPR.2015.7298965
  12. [12] K. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask R-CNN,” Proc. of 2017 IEEE Int. Conf. on Computer Vision (ICCV), pp. 2980-2988, 2017. https://doi.org/10.1109/ICCV.2017.322
  13. [13] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “ImageNet: A large-scale hierarchical image database,” Proc. of 2009 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 248-255, 2009. https://doi.org/10.1109/CVPR.2009.5206848
  14. [14] T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick, “Microsoft COCO: Common objects in context,” European Conf. on Computer Vision (ECCV2014), pp. 740-755, 2014. https://doi.org/10.1007/978-3-319-10602-1_48
  15. [15] D. Bolya, C. Zhou, F. Xiao, and Y. J. Lee, “YOLACT: Real-time instance segmentation,” Proc. of 2019 IEEE/CVF Int. Conf. on Computer Vision (ICCV), pp. 9156-9165, 2019. https://doi.org/10.1109/ICCV.2019.00925
  16. [16] D. Bolya, C. Zhou, F. Xiao, and Y. J. Lee, “YOLACT++: Better real-time instance segmentation,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.44, No.2, pp. 1108-1121, 2020. https://doi.org/10.1109/TPAMI.2020.3014297
  17. [17] X. Wang, R. Zhang, T. Kong, L. Li, and C. Shen, “Solov2: Dynamic and fast instance segmentation,” Advances in Neural Information Processing Systems, Vol.33, pp. 17721-17732, 2020.
  18. [18] T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, “Feature pyramid networks for object detection,” Proc. of 2017 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 936-944, 2017. https://doi.org/10.1109/CVPR.2017.106
  19. [19] Y. Lee and J. Park, “CenterMask: Real-time anchor-free instance segmentation,” Proc. of 2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 13903-13912, 2020. https://doi.org/10.1109/CVPR42600.2020.01392
  20. [20] K. He, X. Zhang, S. Ren, and J. Sun, “Delving deep into rectifiers: Surpassing human-level performance on imagenet classification,” Proc. of the IEEE Int. Conf. on Computer Vision (ICCV), pp. 1026-1034, 2015. https://doi.org/10.1109/ICCV.2015.123
  21. [21] H. Rezatofighi, N. Tsoi, J. Gwak, A. Sadeghian, I. Reid, and S. Savarese, “Generalized intersection over union: A metric and a loss for bounding box regression,” Proc. of 2019 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 658-666, 2019. https://doi.org/10.1109/CVPR.2019.00075
  22. [22] C. H. Sudre, W. Li, T. Vercauteren, S. Ourselin, and M. J. Cardoso, “Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations,” Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support (DLMIA ML-CDS 2017), pp. 240-248, 2017. https://doi.org/10.1007/978-3-319-67558-9_28
  23. [23] M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, “The cityscapes dataset for semantic urban scene understanding,” Proc. of 2016 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 3213-3223, 2016. https://doi.org/10.1109/CVPR.2016.350
  24. [24] K. Chen, J. Wang, J. Pang et al., “MMDetection: Open MMLab detection toolbox and benchmark,” arXiv:1906.07155, 2019. https://doi.org/10.48550/arXiv.1906.07155

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Apr. 19, 2024