Abstract
Recently, object detection frameworks based on Convolutional Neural Networks (CNNs) have become powerful methods for various tasks of medical image analysis; however, they often struggle with most pathological datasets, which are impossible to annotate all the cells. Obviously, sparse annotations may lead to a seriously miscalculated loss in training, which limits the performance of networks. To address this limitation, we investigate the internal training process of object detection networks. Our core observation is that there is a significant density difference between the regression boxes of the positive instances and negative instances. Our novel Boxes Density Energy (BDE) focuses on utilizing the densities of regression boxes to conduct loss-calibration, which is dedicated to reducing the miscalculated loss, meanwhile to penalizing mispredictions with a relatively more significant loss. Thus BDE can guide networks to be trained along the right direction. Extensive experiments have demonstrated that, BDE on the sparsely annotated pathological dataset can significantly boost the performance of networks, and even with 1.0–1.5% higher recall than networks trained on the fully annotated dataset.
J. Feng and L. Yang—Joint corresponding authors.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015). https://doi.org/10.1109/tpami.2016.2577031
Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017). https://doi.org/10.1109/cvpr.2017.106
Ghiasi, G., Lin, T.Y., Le, Q.V.: NAS-FPN: learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7036–7045 (2019). https://doi.org/10.1109/cvpr.2019.00720
Zhong, Z., Jin, L., Zhang, S., Feng, Z.: DeepText: a unified framework for text proposal generation and text detection in natural images. arXiv preprint arXiv:1605.07314 (2016)
Kong, T., Yao, A., Chen, Y., Sun, F.: HyperNet: towards accurate region proposal generation and joint object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 845–853 (2016). https://doi.org/10.1109/cvpr.2016.98
Guo, C., Fan, B., Zhang, Q., Xiang, S., Pan, C.: AugFPN: improving multi-scale feature learning for object detection. arXiv preprint arXiv:1912.05384 (2019)
Qin, Z., et al.: ThunderNet: towards real-time generic object detection on mobile devices. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6718–6727 (2019). https://doi.org/10.1109/iccv.2019.00682
Zhou, J., Ma, C., Xiong, J., Meng, D.: HR-NET: a highly reliable message-passing mechanism for cluster file system. In: 2011 IEEE Sixth International Conference on Networking, Architecture, and Storage, pp. 364–371. IEEE (2011). https://doi.org/10.1109/nas.2011.21
Schmidt, U., Weigert, M., Broaddus, C., Myers, G.: Cell detection with star-convex polygons. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11071, pp. 265–273. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00934-2_30
Sadafi, A., et al.: Multiclass deep active learning for detecting red blood cell subtypes in brightfield microscopy. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11764, pp. 685–693. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32239-7_76
Zhou, Y., Chen, H., Xu, J., Dou, Q., Heng, P.-A.: IRNet: instance relation network for overlapping cervical cell segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11764, pp. 640–648. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32239-7_71
Xu, M., et al.: Missing labels in object detection. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2019)
Yan, Z., Liang, J., Pan, W., Li, J., Zhang, C.: Weakly-and semi-supervised object detection with expectation-maximization algorithm. arXiv preprint arXiv:1702.08740 (2017)
Zhang, X., Wei, Y., Feng, J., Yang, Y., Huang, T.S.: Adversarial complementary learning for weakly supervised object localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1325–1334 (2018). https://doi.org/10.1109/cvpr.2018.00144
Zhang, X., Wei, Y., Kang, G., Yang, Y., Huang, T.: Self-produced guidance for weakly-supervised object localization. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 610–625. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01258-8_37
Niitani, Y., Akiba, T., Kerola, T., Ogawa, T., Sano, S., Suzuki, S.: Sampling techniques for large-scale object detection from sparsely annotated objects. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6510–6518 (2019). https://doi.org/10.1109/cvpr.2019.00667
Inoue, N., Furuta, R., Yamasaki, T., Aizawa, K.: Cross-domain weakly-supervised object detection through progressive domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5001–5009 (2018). https://doi.org/10.1109/cvpr.2018.00525
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017). https://doi.org/10.1109/iccv.2017.324
Li, B., Liu, Y., Wang, X.: Gradient harmonized single-stage detector. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 8577–8584 (2019). https://doi.org/10.1609/aaai.v33i01.33018577
Acknowledgements
This work was supported by the National Key Research and Development Program of China under grant 2017YFB1002504.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, H. et al. (2020). A Novel Loss Calibration Strategy for Object Detection Networks Training on Sparsely Annotated Pathological Datasets. In: Martel, A.L., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2020. MICCAI 2020. Lecture Notes in Computer Science(), vol 12265. Springer, Cham. https://doi.org/10.1007/978-3-030-59722-1_31
Download citation
DOI: https://doi.org/10.1007/978-3-030-59722-1_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59721-4
Online ISBN: 978-3-030-59722-1
eBook Packages: Computer ScienceComputer Science (R0)
