Unsupervised Learning of Individuals and Categories from Images

Motivated by the existence of highly selective, sparsely firing cells observed in the human medial temporal lobe (MTL), we present an unsupervised method for learning and recognizing object categories from unlabeled images. In our model, a network of nonlinear neurons learns a sparse representation of its inputs through an unsupervised expectation-maximization process. We show that the application of this strategy to an invariant feature-based description of natural images leads to the development of units displaying sparse, invariant selectivity for particular individuals or image categories much like those observed in the MTL data.

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

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

[3]  Geoffrey E. Hinton,et al.  Generative models for discovering sparse distributed representations. , 1997, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[4]  Keiji Tanaka.  Mechanisms of visual object recognition: monkey and human studies , 1997, Current Opinion in Neurobiology.

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

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

[7]  Pietro Perona,et al.  Towards automatic discovery of object categories , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[8]  Pietro Perona,et al.  Object class recognition by unsupervised scale-invariant learning , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[9]  David A. Forsyth,et al.  Matching Words and Pictures , 2003, J. Mach. Learn. Res..

[10]  Bir Bhanu,et al.  A new semi-supervised EM algorithm for image retrieval , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[11]  Yuanqing Li,et al.  Analysis of Sparse Representation and Blind Source Separation , 2004, Neural Computation.

[12]  C. Koch,et al.  Invariant visual representation by single neurons in the human brain , 2005, Nature.

[13]  Alexei A. Efros,et al.  Discovering object categories in image collections , 2005 .

[14]  Marc'Aurelio Ranzato,et al.  Efficient Learning of Sparse Representations with an Energy-Based Model , 2006, NIPS.

[15]  C. Koch,et al.  Sparse Representation in the Human Medial Temporal Lobe , 2006, The Journal of Neuroscience.

[16]  David G. Lowe,et al.  Multiclass Object Recognition with Sparse, Localized Features , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[17]  Thomas Serre,et al.  A feedforward architecture accounts for rapid categorization , 2007, Proceedings of the National Academy of Sciences.

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

[19]  C. Koch,et al.  Sparse but not ‘Grandmother-cell’ coding in the medial temporal lobe , 2008, Trends in Cognitive Sciences.

[20]  Indre V. Viskontas,et al.  Advances in memory research: single-neuron recordings from the human medial temporal lobe aid our understanding of declarative memory , 2008, Current opinion in neurology.

[21]  Rafal Bogacz,et al.  Computational models can replicate the capacity of human recognition memory , 2008, Network.