Abstract
Fully convolutional U-shaped neural networks have largely been the dominant approach for pixel-wise image segmentation. In this work, we tackle two defects that hinder their deployment in real-world applications: 1) Predictions lack uncertainty quantification that may be crucial to many decision-making systems; 2) Large memory storage and computational consumption demanding extensive hardware resources. To address these issues and improve their practicality we demonstrate a few-parameter compact Bayesian convolutional architecture, that achieves a marginal improvement in accuracy in comparison to related work using significantly fewer parameters and compute operations. The architecture combines parameter-efficient operations such as separable convolutions, bilinear interpolation, multi-scale feature propagation and Bayesian inference for per-pixel uncertainty quantification through Monte Carlo Dropout. The best performing configurations required fewer than 2.5 million parameters on diverse challenging datasets with few observations.
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
Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481–2495 (2017)
Brostow, G.J., Shotton, J., Fauqueur, J., Cipolla, R.: Segmentation and recognition using structure from motion point clouds. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5302, pp. 44–57. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-88682-2_5
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with Atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833–851. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_49
Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vision 88(2), 303–338 (2010)
Gal, Y., Ghahramani, Z.: Bayesian convolutional neural networks with Bernoulli approximate variational inference. arXiv preprint arXiv:1506.02158 (2015)
Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation. arXiv preprint arXiv:1506.02157 (2015)
Gal, Y., Hron, J., Kendall, A.: Concrete dropout. In: NeurIPS pp. 3581–3590 (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778. IEEE (2016)
Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR, pp. 4700–4708. IEEE (2017)
Jégou, S., Drozdzal, M., Vazquez, D., Romero, A., Bengio, Y.: The one hundred layers tiramisu: Fully convolutional DenseNets for semantic segmentation. In: CVPR Workshops, pp. 11–19 (2017)
Kendall, A., Badrinarayanan, V., Cipolla, R.: Bayesian SegNet: model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. arXiv preprint arXiv:1511.02680 (2015)
Liang, F., Li, Q., Zhou, L.: Bayesian neural networks for selection of drug sensitive genes. J. Am. Stat. Assoc. 113(523), 955–972 (2018)
Liu, C., et al.: Auto-Deeplab: hierarchical neural architecture search for semantic image segmentation. In: CVPR, pp. 82–92. IEEE (2019)
Long, J., Shelhamer, E., Darrell, T., Berkeley, U.: Fully convolutional networks for semantic segmentation. arXiv preprint arXiv:1411.4038 (2014)
McAllister, R., et al.: Concrete problems for autonomous vehicle safety: advantages of Bayesian deep learning. In: IJCAI, IJCAI 2017, p. 4745–4753. AAAI Press (2017)
Mehta, S., Rastegari, M., Caspi, A., Shapiro, L., Hajishirzi, H.: ESPNet: efficient spatial pyramid of dilated convolutions for semantic segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 561–580. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01249-6_34
Myojin, T., Hashimoto, S., Ishihama, N.: Detecting uncertain BNN outputs on FPGA using monte Carlo dropout sampling. In: Farkaš, I., Masulli, P., Wermter, S. (eds.) ICANN 2020. LNCS, vol. 12397, pp. 27–38. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-61616-8_3
Nekrasov, V., Shen, C., Reid, I.: Template-based automatic search of compact semantic segmentation architectures. In: The IEEE Winter Conference on Applications of Computer Vision, pp. 1980–1989. IEEE (2020)
Nguyen, L.: Bacteria detection with darkfield microscopy (2020). Data retrieved from work at Hochschule Heilbronn. www.kaggle.com/longnguyen2306/bacteria-detection-with-darkfield-microscopy/metadata
Romera, E., Alvarez, J.M., Bergasa, L.M., Arroyo, R.: ErfNet: efficient residual factorized convnet for real-time semantic segmentation. IEEE Trans. Intell. Transp. Syst. 19(1), 263–272 (2017)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Ruiz-del Solar, J., Loncomilla, P., Soto, N.: A survey on deep learning methods for robot vision. arXiv preprint arXiv:1803.10862 (2018)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Taghanaki, S.A., et al.: Combo loss: handling input and output imbalance in multi-organ segmentation. Comput. Med. Imaging Graph., 24–33 (2019)
Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: BiSeNet: bilateral segmentation network for real-time semantic segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 334–349. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01261-8_20
Zhang, R.: Making convolutional networks shift-invariant again. arXiv preprint arXiv:1904.11486 (2019)
Zhao, H., Qi, X., Shen, X., Shi, J., Jia, J.: ICNet for real-time semantic segmentation on high-resolution images. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 418–434. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01219-9_25
Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: CVPR, pp. 2881–2890. IEEE (2017)
Zhu, Y., et al.: Improving semantic segmentation via video propagation and label relaxation. In: CVPR, pp. 8856–8865. IEEE (2019)
Acknowledgements
We thank the ICANN 2021 reviewers for useful feedback. Martin Ferianc was sponsored through a scholarship from ICCS at UCL.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Ferianc, M., Manocha, D., Fan, H., Rodrigues, M. (2021). ComBiNet: Compact Convolutional Bayesian Neural Network for Image Segmentation. In: Farkaš, I., Masulli, P., Otte, S., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2021. ICANN 2021. Lecture Notes in Computer Science(), vol 12893. Springer, Cham. https://doi.org/10.1007/978-3-030-86365-4_39
Download citation
DOI: https://doi.org/10.1007/978-3-030-86365-4_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86364-7
Online ISBN: 978-3-030-86365-4
eBook Packages: Computer ScienceComputer Science (R0)