2018

Data Augmentation using Random Image Cropping and Patching for Deep CNNs

Takahashi, Ryo, Matsubara, Takashi, Uehara, Kuniaki

Understand

Deep convolutional neural networks (CNNs) have achieved remarkable results in image processing tasks.

However, their high expression ability risks overfitting.
Consequently, data augmentation techniques have been proposed to prevent overfitting while enriching datasets.
Recent CNN architectures with more parameters are rendering traditional data augmentation techniques insufficient.

Built on

Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel, “Backpropagation Applied to Handwritten Zip Code Recognition,” Neural Computation , vol. 1, no. 4, pp. 541–551, 1989
1989
Earlier work this paper cites.
J. Sietsma and R. J. Dow, “Creating artificial neural networks that generalize,” Neural Networks , vol. 4, no. 1, pp. 67–79, 1991
1991
Earlier work this paper cites.
A. Krizhevsky, “Learning Multiple Layers of Features from Tiny Images,” Technical report, University of Toronto , pp. 1–60, 2009
2009
Earlier work this paper cites.
V. Nair and G. E. Hinton, “Rectified Linear Units Improve Restricted Boltzmann Machines,” in Proc. of the 27th International Conference on Machine Learning (ICML2010) , no. 3, 2010, pp. 807–814
2010
Earlier work this paper cites.
D. C. Ciresan, U. Meier, J. Masci, L. M. Gambardella, and U. JSchmidhuber, “Flexible, High Performance Convolutional Neural Networks for Image Classification,” in Proc. of the International Joint Conference on Artificial Intelligence (IJCAI 2011) , 2011, pp. 1237–1242
2011
Earlier work this paper cites.
D. Cireşan, U. Meier, and J. Schmidhuber, “Multi-column Deep Neural Networks for Image Classification,” in Proc. of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2012) , 2012, pp. 3642–3649
2012
Earlier work this paper cites.
A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” in Advances in Neural Information Processing Systems (NIPS2012) , 2012, pp. 1097–1105
2012
Earlier work this paper cites.
G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. R. Salakhutdinov, “Improving neural networks by preventing co-adaptation of feature detectors,” arXiv , pp. 1–18, 2012
2012
Earlier work this paper cites.
M. D. Zeiler and R. Fergus, “Visualizing and Understanding Convolutional Networks,” in Proc. of European Conference on Computer Vision (ECCV2014) , 2014, pp. 818–833
2014
Earlier work this paper cites.
P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus, and Y. LeCun, “OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks,” in Proc. of International Conference on Learning Representations (ICLR2014) , 2014, pp. 1–16
2014
Earlier work this paper cites.
O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, and C. V. Jan, “ImageNet Large Scale Visual Recognition Challenge,” arXiv , pp. 1–43, 2014
2014
Earlier work this paper cites.
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,” in Proc. of European Conference on Computer Vision (ECCV2014) , 2014, pp. 740–755
2014
Earlier work this paper cites.
G. Hinton, O. Vinyals, and J. Dean, “Distilling the Knowledge in a Neural Network,” in Workshop on Advances in Neural Information Processing Systems (NIPS2014) , 2014, pp. 1–9
2014
Earlier work this paper cites.
R. Kiros, R. Salakhutdinov, and R. S. Zemel, “Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models,” in Workshop on Advances in Neural Information Processing Systems (NIPS2014) , 2014, pp. 1–13
2014
Earlier work this paper cites.
D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” arXiv , pp. 1–15, 2014
2014
Earlier work this paper cites.
C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going deeper with convolutions,” in Proc. of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2015) , vol. 07-12-June, 2015, pp. 1–9
2015
Earlier work this paper cites.

Similar

K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” in Proc. of International Conference on Learning Representations (ICLR2015) , 2015, pp. 1–14
2015
Cited alongside, same era.
I. J. Goodfellow, J. Shlens, and C. Szegedy, “Explaining and Harnessing Adversarial Examples,” in Proc. of International Conference on Learning Representations (ICLR2015) , 2015, pp. 1–11
2015
Cited alongside, same era.
C. Y. Lee, S. Xie, P. Gallagher, Z. Zhang, and Z. Tu, “Deeply-supervised nets,” in Proc. of the 18th International Conference on Artificial Intelligence and Statistics (AISTATS2015) , vol. 2, 2015, pp. 562–570
2015
Cited alongside, same era.
A. Romero, N. Ballas, S. E. Kahou, A. Chassang, C. Gatta, and Y. Bengio, “Fitnets: Hints for Thin Deep Nets,” in Proc. of International Conference on Learning Representations (ICLR2015) , 2015, pp. 1–13
2015
Cited alongside, same era.
J. T. Springenberg, A. Dosovitskiy, T. Brox, and M. Riedmiller, “Striving for Simplicity: The All Convolutional Net,” in Proc. of International Conference on Learning Representations (ICLR2015) , 2015, pp. 1–14
2015
Cited alongside, same era.
S. Ioffe and C. Szegedy, “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift,” in Proc. of the 32th International Conference on Machine Learning (ICML2015) , 2015, pp. 448–456
2015
Cited alongside, same era.
L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang, and Q. Tian, “Scalable Person Re-identification : A Benchmark,” in Proc. of the International Conference on Computer Vision(ICCV2015) , 2015, pp. 1116–1124
2015
Cited alongside, same era.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in Proc. of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2016) , 2016, pp. 770–778
2016
Cited alongside, same era.
K. He and X. Zhang, “Identity mappings in deep residual networks,” Lecture Notes in Computer Science , vol. 9908, no. 1, pp. 630–645, 2016
2016
Cited alongside, same era.
S. Zagoruyko and N. Komodakis, “Wide Residual Networks,” Proc. of the British Machine Vision Conference (BMVC2016) , pp. 87.1–87.12, 2016
2016
Cited alongside, same era.
C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. B. Wojna, “Rethinking the Inception Architecture for Computer Vision,” in Proc. of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2016) , 2016, pp. 2818–2826
2016
Cited alongside, same era.
B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba, “Learning Deep Features for Discriminative Localization,” in Proc. of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2016) , 2016, pp. 2921–2929
2016
Cited alongside, same era.

Then

G. Huang, Z. Liu, and K. Q. Weinberger, “Densely Connected Convolutional Networks,” in Proc. of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2017 ) , 2017, pp. 2261–2269
2017
Later among the works it cites.
D. Han, J. Kim, and J. Kim, “Deep Pyramidal Residual Networks,” in Proc. of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2017 ) , 2017, pp. 6307–6315
2017
Later among the works it cites.
S. Xie, R. Girshick, P. Dollár, Z. Tu, and K. He, “Aggregated residual transformations for deep neural networks,” in Proc. of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2017 ) , 2017, pp. 5987–5995
2017
Later among the works it cites.
T. DeVries and G. W. Taylor, “Improved Regularization of Convolutional Neural Networks with Cutout,” arXiv , pp. 1–8, 2017
2017
Later among the works it cites.
Z. Zhong, L. Zheng, G. Kang, S. Li, and Y. Yang, “Random Erasing Data Augmentation,” arXiv , pp. 1–10, 2017
2017
Later among the works it cites.
B. Zoph and Q. V. Le, “Neural Architecture Search with Reinforcement Learning,” in Proc. of International Conference on Learning Representations (ICLR2017) , 2017, pp. 1–16
2017
Later among the works it cites.
X. Gastaldi, “Shake-Shake regularization,” in ICLR Workshop , 2017, pp. 1–10
2017
Later among the works it cites.
L. Zheng, Y. Yang, and A. G. Hauptmann, “Person Re-identification : Past , Present and Future,” ACM Trans. Multimedia Comput. Commun. Appl. , vol. 14, no. 1, pp. 13:1–13:20, 2017
2017
Later among the works it cites.
H. Zhang, M. Cisse, Y. N. Dauphin, and D. Lopez-Paz, “mixup: Beyond Empirical Risk Minimization,” in Proc. of International Conference on Learning Representations (ICLR2018) , 2018, pp. 1–13
2018
Closest in time.
R. Takahashi, T. Matsubara, and K. Uehara, “RICAP : Random Image Cropping and Patching Data Augmentation for Deep CNNs,” in Proc. of Asian Conference on Machine Learning (ACML2018) , 2018 (accepted)
2018
Closest in time.
E. D. Cubuk, B. Zoph, D. Mane, V. Vasudevan, and Q. V. Le, “AutoAugment: Learning Augmentation Policies from Data,” arXiv , pp. 1–14, 2018
2018
Closest in time.
F. Faghri, D. J. Fleet, J. R. Kiros, and S. Fidler, “VSE++: Improving Visual-Semantic Embeddings with Hard Negatives,” in Proc. of the British Machine Vision Conference (BMVC2018) , 2018, pp. 1–13
2018
Closest in time.
S. W. Yifan Sun, Liang Zheng, Yi Yang, Qi Tian, “Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline),” in Proc. of the European Conference on Computer Vision (ECCV2018) , 2018, pp. 480–496
2018
Closest in time.
J. Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement,” arXiv , pp. 1–6, 2018
2018
Closest in time.
D. Zhao, G. Yu, P. Xu, and M. Luo, “Equivalence between dropout and data augmentation : a mathematical check,” Neural Networks , vol. 115, pp. 82–89, 2019
2019
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…