Look-Ahead Before You Leap: End-to-End Active Recognition by Forecasting the Effect of Motion

Visual recognition systems mounted on autonomous moving agents face the challenge of unconstrained data, but simultaneously have the opportunity to improve their performance by moving to acquire new views of test data. In this work, we first show how a recurrent neural network-based system may be trained to perform end-to-end learning of motion policies suited for this "active recognition" setting. Further, we hypothesize that active vision requires an agent to have the capacity to reason about the effects of its motions on its view of the world. To verify this hypothesis, we attempt to induce this capacity in our active recognition pipeline, by simultaneously learning to forecast the effects of the agent's motions on its internal representation of the environment conditional on all past views. Results across two challenging datasets confirm both that our end-to-end system successfully learns meaningful policies for active category recognition, and that "learning to look ahead" further boosts recognition performance.

[1]  F. Brentano.  Psychologie vom empirischen Standpunkte , 1874 .

[2]  Yiannis Aloimonos,et al.  Active vision , 2004, International Journal of Computer Vision.

[3]  Dana H. Ballard,et al.  Animate Vision , 1991, Artif. Intell..

[4]  John K. Tsotsos,et al.  Active object recognition , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[5]  Sven J. Dickinson,et al.  Active Object Recognition Integrating Attention and Viewpoint Control , 1997, Comput. Vis. Image Underst..

[6]  Bernt Schiele,et al.  Transinformation for active object recognition , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[7]  Lucas Paletta,et al.  Active Object Recognition in Parametric Eigenspace , 1998, BMVC.

[8]  Lucas Paletta,et al.  Active object recognition by view integration and reinforcement learning , 2000, Robotics Auton. Syst..

[9]  Joachim Denzler,et al.  Information Theoretic Sensor Data Selection for Active Object Recognition and State Estimation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[11]  Frank P. Ferrie,et al.  Active Object Recognition: Looking for Differences , 2001, International Journal of Computer Vision.

[12]  Michael H. Bowling,et al.  Action respecting embedding , 2005, ICML.

[13]  Yiannis Aloimonos,et al.  Active segmentation for robotics , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[14]  Stefano Soatto,et al.  Actionable information in vision , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[15]  John K. Tsotsos,et al.  A theory of active object localization , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[16]  Nicholas J. Butko,et al.  Optimal scanning for faster object detection , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  James J. Little,et al.  Semantic Robot Vision Challenge: Current State and Future Directions , 2009, ArXiv.

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

[19]  Risto Miikkulainen,et al.  Learning geometry from sensorimotor experience , 2011, 2011 IEEE International Conference on Development and Learning (ICDL).

[20]  Xiaodong Yu,et al.  Active scene recognition with vision and language , 2011, 2011 International Conference on Computer Vision.

[21]  Nando de Freitas,et al.  Learning attentional policies for tracking and recognition in video with deep networks , 2011, ICML.

[22]  Axel Pinz,et al.  Active Object Categorization on a Humanoid Robot , 2011, VISAPP.

[23]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[24]  Krista A. Ehinger,et al.  Recognizing scene viewpoint using panoramic place representation , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  John K. Tsotsos,et al.  50 Years of object recognition: Directions forward , 2013, Comput. Vis. Image Underst..

[26]  Graham W. Taylor,et al.  "Mental Rotation" by Optimizing Transforming Distance , 2014, ArXiv.

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

[28]  Alan Yuille,et al.  Active Vision , 2014, Computer Vision, A Reference Guide.

[29]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[30]  Alex Graves,et al.  Recurrent Models of Visual Attention , 2014, NIPS.

[31]  Abel Gonzalez-Garcia,et al.  An active search strategy for efficient object detection , 2014, ArXiv.

[32]  Martial Hebert,et al.  Dense Optical Flow Prediction from a Static Image , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[33]  Antonio Torralba,et al.  Anticipating the future by watching unlabeled video , 2015, ArXiv.

[34]  Max Welling,et al.  Transformation Properties of Learned Visual Representations , 2014, ICLR.

[35]  Yoshua Bengio,et al.  Show, Attend and Tell: Neural Image Caption Generation with Visual Attention , 2015, ICML.

[36]  Joshua B. Tenenbaum,et al.  Deep Convolutional Inverse Graphics Network , 2015, NIPS.

[37]  Pierre Sermanet,et al.  Attention for Fine-Grained Categorization , 2014, ICLR.

[38]  Koray Kavukcuoglu,et al.  Multiple Object Recognition with Visual Attention , 2014, ICLR.

[39]  Jianxiong Xiao,et al.  3D ShapeNets: A deep representation for volumetric shapes , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Abel Gonzalez-Garcia,et al.  An active search strategy for efficient object class detection , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Martin A. Riedmiller,et al.  Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images , 2015, NIPS.

[42]  Kristen Grauman,et al.  Learning Image Representations Tied to Ego-Motion , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[43]  Jianxiong Xiao,et al.  DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[44]  Jitendra Malik,et al.  Learning to See by Moving , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[45]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[46]  Song Wu,et al.  3 D ShapeNets : A Deep Representation for Volumetric Shape Modeling , 2015 .

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

[48]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[49]  Javier R. Movellan,et al.  Deep Q-learning for Active Recognition of GERMS: Baseline performance on a standardized dataset for active learning , 2015, BMVC.

[50]  Kristen Grauman,et al.  Slow and Steady Feature Analysis: Higher Order Temporal Coherence in Video , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[51]  John Flynn,et al.  Deep Stereo: Learning to Predict New Views from the World's Imagery , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[52]  Sergey Levine,et al.  End-to-End Training of Deep Visuomotor Policies , 2015, J. Mach. Learn. Res..