Abstract
Whilst it is a trivial task for a human vision system to recognize and detect objects with good accuracy, making computer vision algorithms achieve the same feat remains an active area of research. For a human vision system, objects seen once are recognized with high accuracy despite alterations to its appearance by various transformations such as rotations, translations, scale, distortions and occlusion making it a state-of-the-art spatially invariant biological vision system. To make computer algorithms such as Convolutional Neural Networks (CNNs) spatially invariant one popular practice is to introduce variations in the data set through data augmentation. This achieves good results but comes with increased computation cost. In this paper, we address rotation transformation and instead of using data augmentation we propose a novel method that allows CNNs to improve rotation invariance by augmentation of feature maps. This is achieved by creating a rotation transformer layer called Rotation Invariance Transformer (RiT) that can be placed at the output end of a convolution layer. Incoming features are rotated by a given set of rotation parameters which are then passed to the next layer. We test our technique on benchmark CIFAR10 and MNIST datasets in a setting where our RiT layer is placed between the feature extraction and classification layers of the CNN. Our results show promising improvements in the networks ability to be rotation invariant across classes with no increase in model parameters.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Cheng, G., Zhou, P., Han, J.: Learning rotation-invariant convolutional neural networks for object detection in VHR optical remote sensing images. IEEE Trans. Geosci. Remote Sens. 54(12), 7405–7415 (2016)
Cheng, G., Zhou, P., Han, J.: RIFD-CNN: rotation-invariant and fisher discriminative convolutional neural networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2884–2893 (2016)
Dicarlo, J., Zoccolan, D., Rust, N.C.: How does the brain solve visual object recognition? Neuron 73, 415–434 (2012). https://doi.org/10.1016/j.neuron.2012.01.010
Dieleman, S., Willett, K.W., Dambre, J.: Rotation-invariant convolutional neural networks for galaxy morphology prediction. Mon. Not. Roy. Astron. Soc. 450(2), 1441–1459 (2015)
Follmann, P., Bottger, T.: A rotationally-invariant convolution module by feature map back-rotation. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 784–792. IEEE (2018)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)
Heaton, J.: Introduction to Neural Networks for Java, 2nd edn. Heaton Research Inc., Chesterfield (2008)
Hosseini, H., Xiao, B., Jaiswal, M., Poovendran, R.: On the limitation of convolutional neural networks in recognizing negative images. In: 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 352–358. IEEE (2017)
Hubel, D.H., Wiesel, T.N.: Receptive fields of single neurons in the cat’s striate cortex. J. Physiol. 148, 574–591 (1959)
Hubel, D.H., Wiesel, T.N.: Receptive fields and functional architecture of monkey striate cortex. J. Physiol. 195, 215–243 (1968)
Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. In: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems 28, pp. 2017–2025. Curran Associates Inc., New York (2015)
Kauderer-Abrams, E.: Quantifying translation-invariance in convolutional neural networks. arXiv preprint arXiv:1801.01450 (2017)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images. Technical report. Citeseer (2009)
Kyrki, V.: Local and global feature extraction for invariant object recognition. Ph.D. thesis, Lappeenrannan University of Technology, Finland (2002)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
LeCun, Y., Cortes, C., Burges, C.: The MNIST database of handwritten digits. Technical report (1998)
Lenc, K., Vedaldi, A.: Understanding image representations by measuring their equivariance and equivalence. In: CVPR (2015)
Marcos, D., Volpi, M., Tuia, D.: Learning rotation invariant convolutional filters for texture classification. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 2012–2017. IEEE (2016)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Xu, Y., Xiao, T., Zhang, J., Yang, K., Zhang, Z.: Scale-invariant convolutional neural networks. CoRR abs/1411.6369 (2014). http://arxiv.org/abs/1411.6369
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
Kumar, D., Sharma, D., Goecke, R. (2020). Feature Map Augmentation to Improve Rotation Invariance in Convolutional Neural Networks. In: Blanc-Talon, J., Delmas, P., Philips, W., Popescu, D., Scheunders, P. (eds) Advanced Concepts for Intelligent Vision Systems. ACIVS 2020. Lecture Notes in Computer Science(), vol 12002. Springer, Cham. https://doi.org/10.1007/978-3-030-40605-9_30
Download citation
DOI: https://doi.org/10.1007/978-3-030-40605-9_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-40604-2
Online ISBN: 978-3-030-40605-9
eBook Packages: Computer ScienceComputer Science (R0)