Improving invariance in visual classification with biologically inspired mechanism

A computational model of visual cortex has raised great interest in developing algorithms mimicking human visual systems. The max-operation is employed in the model to emulate the scale and position invariant responses of the visual cells. We further extend this idea to enhance the tolerance of visual classification against the general intra-class variability. A general architecture of the basic block constituting the model is first presented. The architecture adaptively chooses the best matching template from a set of competing templates to predict the label of the incoming sample. To optimize the non-convex and non-smooth objective function resulted, we develop an algorithm to train each template alternately. Experiments show that the proposed method significantly outperforms linear classifiers as a template matching method in several image classification tasks, and is much more computationally efficient than other commonly used non-linear classifiers. In the image classification task on the Caltech 101 database, the performance of the biologically inspired model is obviously boosted by incorporating the proposed method.

[1]  Tomaso Poggio,et al.  Generalization in vision and motor control , 2004, Nature.

[2]  N. Logothetis,et al.  Shape representation in the inferior temporal cortex of monkeys , 1995, Current Biology.

[3]  Xuelong Li,et al.  Biologically Inspired Features for Scene Classification in Video Surveillance , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[4]  Ângelo Cardoso,et al.  Handwritten digit recognition using biologically inspired features , 2013, Neurocomputing.

[5]  A. K. Rigler,et al.  Accelerating the convergence of the back-propagation method , 1988, Biological Cybernetics.

[6]  Paul A. Viola,et al.  Detecting Pedestrians Using Patterns of Motion and Appearance , 2005, International Journal of Computer Vision.

[7]  Ramakant Nevatia,et al.  Cluster Boosted Tree Classifier for Multi-View, Multi-Pose Object Detection , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[8]  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).

[9]  Dariu Gavrila,et al.  A mixed generative-discriminative framework for pedestrian classification , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Dacheng Tao,et al.  Biologically inspired feature manifold for gait recognition , 2010, Neurocomputing.

[11]  Liang-Tien Chia,et al.  Scene classification using multiple features in a two-stage probabilistic classification framework , 2010, Neurocomputing.

[12]  Lambert Schomaker,et al.  Handwritten-Word Spotting Using Biologically Inspired Features , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[14]  D. Hubel,et al.  Receptive fields, binocular interaction and functional architecture in the cat's visual cortex , 1962, The Journal of physiology.

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

[16]  Federico Girosi,et al.  Training support vector machines: an application to face detection , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[17]  Xuelong Li,et al.  Enhanced Biologically Inspired Model for Object Recognition , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[18]  Thomas Serre,et al.  Categorization by Learning and Combining Object Parts , 2001, NIPS.

[19]  Bo Wu,et al.  Fast rotation invariant multi-view face detection based on real Adaboost , 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..

[20]  David G. Lowe,et al.  University of British Columbia. , 1945, Canadian Medical Association journal.

[21]  Lior Wolf,et al.  Using Biologically Inspired Features for Face Processing , 2007, International Journal of Computer Vision.

[22]  David D. Cox,et al.  Opinion TRENDS in Cognitive Sciences Vol.11 No.8 Untangling invariant object recognition , 2022 .

[23]  T. Poggio,et al.  Direction estimation of pedestrian from multiple still images , 2004, IEEE Intelligent Vehicles Symposium, 2004.

[24]  Jitendra Malik,et al.  SVM-KNN: Discriminative Nearest Neighbor Classification for Visual Category Recognition , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

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

[26]  T. Poggio,et al.  Cognitive neuroscience: Neural mechanisms for the recognition of biological movements , 2003, Nature Reviews Neuroscience.

[27]  Thomas Serre,et al.  A neuromorphic approach to computer vision , 2010, Commun. ACM.

[28]  Aníbal R. Figueiras-Vidal,et al.  Committees of Adaboost ensembles with modified emphasis functions , 2010, Neurocomputing.

[29]  Jing Li,et al.  A comprehensive review of current local features for computer vision , 2008, Neurocomputing.

[30]  Donald Geman,et al.  Coarse-to-Fine Face Detection , 2004, International Journal of Computer Vision.

[31]  Yuan Li,et al.  High-Performance Rotation Invariant Multiview Face Detection , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  T. Poggio,et al.  Hierarchical models of object recognition in cortex , 1999, Nature Neuroscience.

[33]  Tom Tollenaere,et al.  SuperSAB: Fast adaptive back propagation with good scaling properties , 1990, Neural Networks.

[34]  Thomas Serre,et al.  Robust Object Recognition with Cortex-Like Mechanisms , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[35]  Tomaso A. Poggio,et al.  Full-body person recognition system , 2003, Pattern Recognit..

[36]  Mahdieh Soleymani Baghshah,et al.  Kernel-based metric learning for semi-supervised clustering , 2010, Neurocomputing.

[37]  Hyun Seung Yang,et al.  A face detection using biologically motivated bottom-up saliency map model and top-down perception model , 2004, Neurocomputing.