Motion Invariance in Visual Environments

The puzzle of computer vision might find new challenging solutions when we realize that most successful methods are working at image level, which is remarkably more difficult than processing directly visual streams, just as happens in nature. In this paper, we claim that their processing naturally leads to formulate the motion invariance principle, which enables the construction of a new theory of visual learning based on convolutional features. The theory addresses a number of intriguing questions that arise in natural vision, and offers a well-posed computational scheme for the discovery of convolutional filters over the retina. They are driven by the Euler-Lagrange differential equations derived from the principle of least cognitive action, that parallels laws of mechanics. Unlike traditional convolutional networks, which need massive supervision, the proposed theory offers a truly new scenario in which feature learning takes place by unsupervised processing of video signals. An experimental report of the theory is presented where we show that features extracted under motion invariance yield an improvement that can be assessed by measuring information-based indexes.

[1]  H. J. Gamble.  Trends in Neurosciences , 1980 .

[2]  Cordelia Schmid,et al.  Actions in context , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Trevor Darrell,et al.  Learning Features by Watching Objects Move , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  M. Goodale,et al.  Separate visual pathways for perception and action , 1992, Trends in Neurosciences.

[5]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[6]  Richard Szeliski,et al.  A Database and Evaluation Methodology for Optical Flow , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[7]  Marco Gori,et al.  Unsupervised Learning by Minimal Entropy Encoding , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[8]  Marco Gori,et al.  Information Theoretic Learning for Pixel-Based Visual Agents , 2012, ECCV.

[9]  Marc'Aurelio Ranzato,et al.  Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[11]  Y-Lan Boureau,et al.  Learning Convolutional Feature Hierarchies for Visual Recognition , 2010, NIPS.

[12]  Terrence J. Sejnowski,et al.  Slow Feature Analysis: Unsupervised Learning of Invariances , 2002, Neural Computation.

[13]  Fabio Anselmi,et al.  Visual Cortex and Deep Networks: Learning Invariant Representations , 2016 .

[14]  Lin Sun,et al.  DL-SFA: Deeply-Learned Slow Feature Analysis for Action Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[16]  Marco Gori,et al.  Semantic video labeling by developmental visual agents , 2016, Comput. Vis. Image Underst..

[17]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[18]  Cordelia Schmid,et al.  Actions in context , 2009, CVPR.

[19]  Marco Gori,et al.  The principle of least cognitive action , 2016, Theor. Comput. Sci..