Deep Caps Going Deeper with Capsule Networks Jathushan
- Slides: 34
Deep. Caps : Going Deeper with Capsule Networks Jathushan Rajasegaran Hirunima Jayasekara Vinoj Jayasundara Suranga Seneviratne June 20 2019 Sandaru Jayasekara Ranga Rodrigo
Capsule Neural Networks [1] S. Sabour, N. Frosst, and G. E. Hinton, “Dynamic routing between capsules, ” in NIPS, Long Beach, CA, 2017
Motivation MNIST - low level feature representation CIFAR 10 - high level feature representation Achieves SOTA on MNIST (99. 75%) [1] Only 89. 6% on CIFAR 10 With 7 -ensembles. [1] S. Sabour, N. Frosst, and G. E. Hinton, “Dynamic routing between capsules, ” in NIPS, Long Beach, CA, 2017
Goals 1. High level understanding with capsules 2. Joint representation of classes with instantiation parameters 3. Computationally efficient network
Inspired by Conventional CNNs Alex. Net [1] VGG Net [2] Goog. Le. Net [3] Res. Net [4] [1] [2] [3] [4] A. Krizhevsky, I. Sutskever, and G. Hinton. Imagenet classificationwith deep convolutional neural networks. In NIPS, 2012 S. Ren, K. He, R. Girshick, and J. Sun. Faster R-CNN: Towardsreal-time object detection with region proposal networks. In NIPS, 2015 C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Er-han, V. Vanhoucke, and A. Rabinovich. Going deeper with convolutions. In CVPR, 2015 K. He, X. Zhang, and S. Ren, “Deep residual learning for image recognition, ” in CVPR, 2016
Proposed Deep Capsule Networks Conv. Caps Layer Caps. Cell
Conv. Caps layer
Conv. Caps layer
Conv. Caps layer
Conv. Caps layer
Conv. Caps layer
Conv. Caps layer
Conv. Caps layer
Conv. Caps layer
Conv. Caps layer
Conv. Caps layer
Conv. Caps layer
Conv. Caps layer
Conv. Caps layer
Conv. Caps layer
Conv. Caps layer
Conv. Caps layer
Conv. Caps layer
Conv. Caps layer
Conv. Caps layer
Conv. Caps layer
Conv. Caps layer
Class Independent Decoder
Results - Error Rates on CIFAR 10 - Test Error (%) 35 30 25 20 15 Ours 10 5 Conventional CNNs Deep. Capsule. Net Nair et al. Hit. Net DPN Res. Net Dense. Net 0 Capsule domain networks
Results - Performance on other datasets Model CIFAR 10 SVHN F-MNIST Dense. Net [1] Res. Net [2] DPN [3] Wan et al. [4] Zhong et al. [5] Sabour et al. [6] Nair et al. [7] Hit. Net [8] Deep. Caps (7 -ensembles) 96. 40% 93. 57% 96. 35% 96. 92% 89. 40% 67. 53% 73. 30% 91. 01% 92. 74% 98. 41% 95. 70% 91. 06 % 94. 50% 97. 16% 97. 56% 95. 40% 95. 70% 96. 35% 93. 60% 89. 80% 92. 30% 94. 46% 94. 73% 99. 59% 99. 75% 99. 50% 99. 68% 99. 72% - [1] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Wein- berger, “Densely connected convolutional networks. ” in CVPR, 2017. [2] K. He, X. Zhang, S. Ren, and. J. Sun, “Deepresiduallearning for image recognition, ” in CVPR , 2016. [3] Y. Chen, J. Li, H. Xiao, X. Jin, S. Yan, and J. Feng, “Dual path networks, ” in NIPS, 2017. [4] L. Wan, M. Zeiler, S. Zhang, Y. L. Cun, and. R. Fergus, “Reg- ularization of neural networks using dropconnect, ” ICML , 2013. [5] Z. Zhong, L. Zheng, G. Kang, S. Li, and Y. Yang, “Random erasing data augmentation, ” Co. RR, 2017. [6] S. Sabour, N. Frosst, and G. E. Hinton, “Dynamic routing be- tween capsules, ” in NIPS, 2017. [7] P. Q. Nair, R. Doshi, and S. Keselj, “Pushing the limits of capsule networks, ” 2018. [8] A. Delie`ge, A. Cioppa, and. M. Van. Droogenbroeck, “Hitnet: a neural network with capsules embedded in a hit-or-miss layer, extended with hybrid data augmentation and ghost capsules, ” Co. RR, 2018.
Results - Instantiation parameter perturbation
Results Rotation (10) Vertical elongation (18) Thickness (1) Vertical expansion (30) Localized skewness (6)
Results
Thank You!
- Into the heart of jesus deeper and deeper i go
- Tic tac toe going high going low going criss cross lollipop
- Definition of soft gelatin capsule
- Deep forest: towards an alternative to deep neural networks
- Capsule networks tutorial
- If you are going through hell, keep going
- Deep asleep deep asleep it lies
- 深哉深哉
- Mippers
- Deep convolutional networks
- Image super resolution using deep convolutional networks
- Convolutional deep belief networks
- Distbelief
- Efficient processing of deep neural networks pdf
- Greedy layer wise training of deep networks
- Difference between virtual circuit and datagram
- Basestore iptv
- Dive deep synonyms
- Growing deeper in god
- Dclm netherlands
- Deeper life netherlands
- Deeper life netherlands
- Deeper life bible church netherlands search the scriptures
- Deeper life canada
- "we thinkers" curriculum or methodology or vocabulary
- Deeper life bible church netherlands
- Promote together
- Deeper life bible church netherlands
- Netherlands
- Deeper exam
- Deeper life netherlands
- Deeper life netherlands
- Your love is deeper than the ocean higher than the heavens
- Deeper life bible church
- Deeper life bible church netherlands search the scriptures