Skip to main content

Tipp

Weitere Kapitel dieses Buchs durch Wischen aufrufen

2018 | OriginalPaper | Buchkapitel

Competition vs. Concatenation in Skip Connections of Fully Convolutional Networks

verfasst von : Santiago Estrada, Sailesh Conjeti, Muneer Ahmad, Nassir Navab, Martin Reuter

Erschienen in: Machine Learning in Medical Imaging

Verlag: Springer International Publishing

share
TEILEN

Abstract

Increased information sharing through short and long-range skip connections between layers in fully convolutional networks have demonstrated significant improvement in performance for semantic segmentation. In this paper, we propose Competitive Dense Fully Convolutional Networks (CDFNet) by introducing competitive maxout activations in place of naïve feature concatenation for inducing competition amongst layers. Within CDFNet, we propose two architectural contributions, namely competitive dense block (CDB) and competitive unpooling block (CUB) to induce competition at local and global scales for short and long-range skip connections respectively. This extension is demonstrated to boost learning of specialized sub-networks targeted at segmenting specific anatomies, which in turn eases the training of complex tasks. We present the proof-of-concept on the challenging task of whole body segmentation in the publicly available VISCERAL benchmark and demonstrate improved performance over multiple learning and registration based state-of-the-art methods.
Fußnoten
1
Multi-Atlas Registration via Markov Random Field, Right Psoas Muscle excluded
 
2
Multi-Atlas Registration w/discrete optimization and self-similarities, Occluded organs only Gallbladder
 
Literatur
1.
Zurück zum Zitat 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) CrossRef 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) CrossRef
3.
Zurück zum Zitat He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778 (2016) He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778 (2016)
4.
Zurück zum Zitat Huang, G., Liu, Z., Weinberger, K.Q., van der Maaten, L.: Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, vol. 1, p. 3 (2017) Huang, G., Liu, Z., Weinberger, K.Q., van der Maaten, L.: Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, vol. 1, p. 3 (2017)
5.
Zurück zum Zitat Goodfellow, I.J., Warde-Farley, D., Mirza, M., Courville, A., Bengio, Y.: Maxout networks. In: Proceedings of the 30th International Conference on International Conference on Machine Learning-Volume 28, pp. III-1319. JMLR. org (2013) Goodfellow, I.J., Warde-Farley, D., Mirza, M., Courville, A., Bengio, Y.: Maxout networks. In: Proceedings of the 30th International Conference on International Conference on Machine Learning-Volume 28, pp. III-1319. JMLR. org (2013)
6.
Zurück zum Zitat Liao, Z., Carneiro, G.: A deep convolutional neural network module that promotes competition of multiple-size filters. Pattern Recognit. 71, 94–105 (2017) CrossRef Liao, Z., Carneiro, G.: A deep convolutional neural network module that promotes competition of multiple-size filters. Pattern Recognit. 71, 94–105 (2017) CrossRef
7.
8.
Zurück zum Zitat Jimenez-del Toro, O., Müller, H., Krenn, M., Gruenberg, K., Taha, A.A., Winterstein, M., Eggel, I., Foncubierta-Rodríguez, A., Goksel, O., Jakab, A.: Cloud-based evaluation of anatomical structure segmentation and landmark detection algorithms: visceral anatomy benchmarks. IEEE Trans. Med. Imaging 35(11), 2459–2475 (2016) CrossRef Jimenez-del Toro, O., Müller, H., Krenn, M., Gruenberg, K., Taha, A.A., Winterstein, M., Eggel, I., Foncubierta-Rodríguez, A., Goksel, O., Jakab, A.: Cloud-based evaluation of anatomical structure segmentation and landmark detection algorithms: visceral anatomy benchmarks. IEEE Trans. Med. Imaging 35(11), 2459–2475 (2016) CrossRef
9.
Zurück zum Zitat Srivastava, R.K., Masci, J., Gomez, F., Schmidhuber, J.: Understanding locally competitive networks. arXiv preprint arXiv:​1410.​1165 (2014) Srivastava, R.K., Masci, J., Gomez, F., Schmidhuber, J.: Understanding locally competitive networks. arXiv preprint arXiv:​1410.​1165 (2014)
10.
Zurück zum Zitat Liao, Z., Carneiro, G.: On the importance of normalisation layers in deep learning with piecewise linear activation units. In: 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1–8. IEEE (2016) Liao, Z., Carneiro, G.: On the importance of normalisation layers in deep learning with piecewise linear activation units. In: 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1–8. IEEE (2016)
11.
Zurück zum Zitat Jégou, S., Drozdzal, M., Vazquez, D., Romero, A., Bengio, Y.: The one hundred layers tiramisu: fully convolutional densenets for semantic segmentation. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1175–1183. IEEE (2017) Jégou, S., Drozdzal, M., Vazquez, D., Romero, A., Bengio, Y.: The one hundred layers tiramisu: fully convolutional densenets for semantic segmentation. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1175–1183. IEEE (2017)
12.
Zurück zum Zitat Roy, A.G., Conjeti, S., Sheet, D., Katouzian, A., Navab, N., Wachinger, C.: Error Corrective Boosting for Learning Fully Convolutional Networks with Limited Data. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 231–239. Springer, Cham (2017). https://​doi.​org/​10.​1007/​978-3-319-66179-7_​27 Roy, A.G., Conjeti, S., Sheet, D., Katouzian, A., Navab, N., Wachinger, C.: Error Corrective Boosting for Learning Fully Convolutional Networks with Limited Data. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 231–239. Springer, Cham (2017). https://​doi.​org/​10.​1007/​978-3-319-66179-7_​27
Metadaten
Titel
Competition vs. Concatenation in Skip Connections of Fully Convolutional Networks
verfasst von
Santiago Estrada
Sailesh Conjeti
Muneer Ahmad
Nassir Navab
Martin Reuter
Copyright-Jahr
2018
DOI
https://doi.org/10.1007/978-3-030-00919-9_25

Premium Partner