Learning to See by Moving

The current dominant paradigm for feature learning in computer vision relies on training neural networks for the task of object recognition using millions of hand labelled images. Is it also possible to learn features for a diverse set of visual tasks using any other form of supervision? In biology, living organisms developed the ability of visual perception for the purpose of moving and acting in the world. Drawing inspiration from this observation, in this work we investigated if the awareness of egomotion(i.e. self motion) can be used as a supervisory signal for feature learning. As opposed to the knowledge of class labels, information about egomotion is freely available to mobile agents. We found that using the same number of training images, features learnt using egomotion as supervision compare favourably to features learnt using class-label as supervision on the tasks of scene recognition, object recognition, visual odometry and keypoint matching.

[1]  J. Gibson.  The Ecological Approach to Visual Perception , 1979 .

[2]  A. Remole.  PERCEPTION WITH AN EYE FOR MOTION , 1987 .

[3]  Yann LeCun,et al.  Modeles connexionnistes de l'apprentissage , 1987 .

[4]  Dean Pomerleau,et al.  ALVINN, an autonomous land vehicle in a neural network , 2015 .

[5]  Lawrence D. Jackel,et al.  Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[6]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[7]  Geoffrey E. Hinton,et al.  The "wake-sleep" algorithm for unsupervised neural networks. , 1995, Science.

[8]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[9]  David J. Field,et al.  Sparse coding with an overcomplete basis set: A strategy employed by V1? , 1997, Vision Research.

[10]  Terrence J. Sejnowski,et al.  The “independent components” of natural scenes are edge filters , 1997, Vision Research.

[11]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[12]  Terrence J. Sejnowski,et al.  Unsupervised Learning , 2018, Encyclopedia of GIS.

[13]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[14]  Pietro Perona,et al.  Unsupervised Learning of Models for Recognition , 2000, ECCV.

[15]  Simon Haykin,et al.  GradientBased Learning Applied to Document Recognition , 2001 .

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

[17]  G. Berkeley.  Essay Towards a New Theory of Vision , 2004 .

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

[19]  H. Bourlard,et al.  Auto-association by multilayer perceptrons and singular value decomposition , 1988, Biological Cybernetics.

[20]  G. Rizzolatti,et al.  The mirror-neuron system. , 2004, Annual review of neuroscience.

[21]  Antonio Torralba,et al.  Describing Visual Scenes using Transformed Dirichlet Processes , 2005, NIPS.

[22]  Alexei A. Efros,et al.  Discovering objects and their location in images , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[23]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[24]  Yann LeCun,et al.  Learning a similarity metric discriminatively, with application to face verification , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[25]  Yoshua Bengio,et al.  Greedy Layer-Wise Training of Deep Networks , 2006, NIPS.

[26]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[27]  Yann LeCun,et al.  Dimensionality Reduction by Learning an Invariant Mapping , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[28]  Alexei A. Efros,et al.  Using Multiple Segmentations to Discover Objects and their Extent in Image Collections , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[29]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[30]  Antonio Torralba,et al.  Building the gist of a scene: the role of global image features in recognition. , 2006, Progress in brain research.

[31]  Yann LeCun,et al.  Online Learning for Offroad Robots: Spatial Label Propagation to Learn Long-Range Traversability , 2007, Robotics: Science and Systems.

[32]  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.

[33]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[34]  C. Stachniss,et al.  Online Learning for Offroad Robots: Using Spatial Label Propagation to Learn Long-Range Traversability , 2008 .

[35]  Honglak Lee,et al.  Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations , 2009, ICML '09.

[36]  Christopher Hunt,et al.  Notes on the OpenSURF Library , 2009 .

[37]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[38]  Geoffrey E. Hinton,et al.  Deep Boltzmann Machines , 2009, AISTATS.

[39]  Hossein Mobahi,et al.  Deep learning from temporal coherence in video , 2009, ICML '09.

[40]  Geoffrey E. Hinton,et al.  Learning to Represent Spatial Transformations with Factored Higher-Order Boltzmann Machines , 2010, Neural Computation.

[41]  Yann LeCun,et al.  Convolutional Learning of Spatio-temporal Features , 2010, ECCV.

[42]  Nicholas J. Butko,et al.  Active perception , 2010 .

[43]  Krista A. Ehinger,et al.  SUN database: Large-scale scene recognition from abbey to zoo , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[44]  Subhransu Maji,et al.  Detecting People Using Mutually Consistent Poselet Activations , 2010, ECCV.

[45]  Andrea Vedaldi,et al.  Vlfeat: an open and portable library of computer vision algorithms , 2010, ACM Multimedia.

[46]  Geoffrey E. Hinton,et al.  Transforming Auto-Encoders , 2011, ICANN.

[47]  Quoc V. Le,et al.  Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis , 2011, CVPR 2011.

[48]  Xin Chen,et al.  City-scale landmark identification on mobile devices , 2011, CVPR 2011.

[49]  H. B. Barlow,et al.  Possible Principles Underlying the Transformations of Sensory Messages , 2012 .

[50]  Christopher K. I. Williams,et al.  The Shape Boltzmann Machine: A Strong Model of Object Shape , 2012, International Journal of Computer Vision.

[51]  Geoffrey E. Hinton,et al.  Robust Boltzmann Machines for recognition and denoising , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[52]  Nitish Srivastava,et al.  Multimodal learning with deep Boltzmann machines , 2012, J. Mach. Learn. Res..

[53]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[54]  Shenghuo Zhu,et al.  Deep Learning of Invariant Features via Simulated Fixations in Video , 2012, NIPS.

[55]  Xiaogang Wang,et al.  Hierarchical face parsing via deep learning , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[56]  Derek Hoiem,et al.  Indoor Segmentation and Support Inference from RGBD Images , 2012, ECCV.

[57]  Alexei A. Efros,et al.  Unsupervised Discovery of Mid-Level Discriminative Patches , 2012, ECCV.

[58]  Pascal Vincent,et al.  Unsupervised Feature Learning and Deep Learning: A Review and New Perspectives , 2012, ArXiv.

[59]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[60]  Marc'Aurelio Ranzato,et al.  Building high-level features using large scale unsupervised learning , 2011, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[61]  Andreas Geiger,et al.  Vision meets robotics: The KITTI dataset , 2013, Int. J. Robotics Res..

[62]  Yann LeCun,et al.  Pedestrian Detection with Unsupervised Multi-stage Feature Learning , 2012, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[63]  Alexei A. Efros,et al.  Mid-level Visual Element Discovery as Discriminative Mode Seeking , 2013, NIPS.

[64]  Martial Hebert,et al.  Data-Driven 3D Primitives for Single Image Understanding , 2013, 2013 IEEE International Conference on Computer Vision.

[65]  Cordelia Schmid,et al.  Action Recognition with Improved Trajectories , 2013, 2013 IEEE International Conference on Computer Vision.

[66]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[67]  Martial Hebert,et al.  Unfolding an Indoor Origami World , 2014, ECCV.

[68]  Marc'Aurelio Ranzato,et al.  Video (language) modeling: a baseline for generative models of natural videos , 2014, ArXiv.

[69]  Yangqing Jia,et al.  Deep Convolutional Ranking for Multilabel Image Annotation , 2013, ICLR.

[70]  Lourdes Agapito,et al.  Reconstructing PASCAL VOC , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[71]  Alexei A. Efros,et al.  Context as Supervisory Signal: Discovering Objects with Predictable Context , 2014, ECCV.

[72]  Yunchao Wei,et al.  Computational Baby Learning , 2014, ArXiv.

[73]  Andrew Zisserman,et al.  Two-Stream Convolutional Networks for Action Recognition in Videos , 2014, NIPS.

[74]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[75]  Trevor Darrell,et al.  DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition , 2013, ICML.

[76]  Marc Pollefeys,et al.  Discriminatively Trained Dense Surface Normal Estimation , 2014, ECCV.

[77]  Thomas Brox,et al.  Descriptor Matching with Convolutional Neural Networks: a Comparison to SIFT , 2014, ArXiv.

[78]  Jitendra Malik,et al.  Analyzing the Performance of Multilayer Neural Networks for Object Recognition , 2014, ECCV.

[79]  Yang Song,et al.  Learning Fine-Grained Image Similarity with Deep Ranking , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[80]  Jonathan Tompson,et al.  Unsupervised Feature Learning from Temporal Data , 2015, ICLR.

[81]  Nir Ailon,et al.  Deep Metric Learning Using Triplet Network , 2014, SIMBAD.

[82]  Jonathan Tompson,et al.  Unsupervised Learning of Spatiotemporally Coherent Metrics , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[83]  Abhinav Gupta,et al.  Designing deep networks for surface normal estimation , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[84]  Rui Caseiro,et al.  High-Speed Tracking with Kernelized Correlation Filters , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[85]  Changsheng Xu,et al.  Matching-CNN meets KNN: Quasi-parametric human parsing , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[86]  Nitish Srivastava,et al.  Unsupervised Learning of Video Representations using LSTMs , 2015, ICML.

[87]  Stefano Soatto,et al.  Visual Scene Representations: Sufficiency, Minimality, Invariance and Deep Approximations , 2014, ICLR.

[88]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[89]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.