publication . Preprint . 2017

Quantifying Translation-Invariance in Convolutional Neural Networks

Kauderer-Abrams, Eric;
Open Access English
  • Published: 10 Dec 2017
A fundamental problem in object recognition is the development of image representations that are invariant to common transformations such as translation, rotation, and small deformations. There are multiple hypotheses regarding the source of translation invariance in CNNs. One idea is that translation invariance is due to the increasing receptive field size of neurons in successive convolution layers. Another possibility is that invariance is due to the pooling operation. We develop a simple a tool, the translation-sensitivity map, which we use to visualize and quantify the translation-invariance of various architectures. We obtain the surprising result that arc...
free text keywords: Computer Science - Computer Vision and Pattern Recognition
Download from

[1] Sundaramoorthi, Ganesh, et al. ”On the set of images modulo viewpoint and contrast changes.” Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on. IEEE, 2009.

[2] LeCun, Yann, et al. ”Gradient-based learning applied to document recognition.” Proceedings of the IEEE 86.11 (1998): 2278-2324.

[3] Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. ”Imagenet classification with deep convolutional neural networks.” Advances in neural information processing systems. 2012.

[4] Gens, Robert, and Pedro M. Domingos. ”Deep symmetry networks.” Advances in neural information processing systems. 2014.

[5] Jaderberg, Max, Karen Simonyan, and Andrew Zisserman. ”Spatial transformer networks.” Advances in Neural Information Processing Systems. 2015. [OpenAIRE]

[6] LeCun, Yann, Corinna Cortes, and Christopher JC Burges. ”The MNIST database of handwritten digits.” (1998).

[7] LeCun, Yann. ”Learning invariant feature hierarchies.” Computer vision?ECCV 2012. Workshops and demonstrations. Springer Berlin Heidelberg, 2012.

[8] Lenc, Karel, and Andrea Vedaldi. ”Understanding image representations by measuring their equivariance and equivalence.” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015. [OpenAIRE]

[9] Bruna, Joan, and Stephane Mallat. ”Invariant scattering convolution networks.” Pattern Analysis and Machine Intelligence, IEEE Transactions on 35.8 (2013): 1872- 1886.

[10] Mallat, Stephane. ”Group invariant scattering.” Communications on Pure and Applied Mathematics 65.10 (2012): 1331-1398.

[11] Soatta, Stegano, and Alessandro Chiuso. ”Visual Representations: Defining Properties and Deep Approximations.” ICLR (2016)

[12] Anselmi, Fabio, et al. ”Unsupervised learning of invariant representations in hierarchical architectures.” arXiv preprint arXiv:1311.4158 (2013). [OpenAIRE]

[13] Kingma, Diederik, and Jimmy Ba. ”Adam: A method for stochastic optimization.” arXiv preprint arXiv:1412.6980 (2014).

[14] Abadi, Martin, et al. ”TensorFlow: Large-scale machine learning on heterogeneous systems, 2015.” Software available from tensorflow. org.

Any information missing or wrong?Report an Issue