Decomposition, discovery and detection of visual categories using topic models

We present a novel method for the discovery and detection of visual object categories based on decompositions using topic models. The approach is capable of learning a compact and low dimensional representation for multiple visual categories from multiple view points without labeling of the training instances. The learnt object components range from local structures over line segments to global silhouette-like descriptions. This representation can be used to discover object categories in a totally unsupervised fashion. Furthermore we employ the representation as the basis for building a supervised multi-category detection system making efficient use of training examples and out-performing pure features-based representations. The proposed speed-ups make the system scale to large databases. Experiments on three databases show that the approach improves the state-of-the-art in unsupervised learning as well as supervised detection. In particular we improve the state-of-the-art on the challenging PASCALpsila06 multi-class detection tasks for several categories.

[1]  J. Barth.  End of the road , 1960 .

[2]  Hilda F. Duncan,et al.  Division by Zero. , 1971 .

[3]  Chuck Allison,et al.  The preprocessor , 1994 .

[4]  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.

[5]  David Haussler,et al.  Exploiting Generative Models in Discriminative Classifiers , 1998, NIPS.

[6]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

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

[8]  Michael McMillan.  Object-Oriented Programming with Visual Basic.NET: Building a Windows Application , 2004 .

[9]  Thomas Hofmann,et al.  Unsupervised Learning by Probabilistic Latent Semantic Analysis , 2004, Machine Learning.

[10]  Mark Steyvers,et al.  Finding scientific topics , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[11]  Bernt Schiele,et al.  Pedestrian detection in crowded scenes , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[12]  Pietro Perona,et al.  A Bayesian hierarchical model for learning natural scene categories , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[13]  Pietro Perona,et al.  Learning object categories from Google's image search , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[14]  Antonio Torralba,et al.  Learning hierarchical models of scenes, objects, and parts , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

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

[16]  Luc Van Gool,et al.  Modeling scenes with local descriptors and latent aspects , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[17]  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).

[18]  Bernt Schiele,et al.  Integrating representative and discriminant models for object category detection , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[19]  Stefano Soatto,et al.  Detecting Humans via Their Pose , 2006, NIPS.

[20]  Jianguo Zhang,et al.  The PASCAL Visual Object Classes Challenge , 2006 .

[21]  Andrew Zisserman,et al.  Scene Classification Via pLSA , 2006, ECCV.

[22]  Luc Van Gool,et al.  The 2005 PASCAL Visual Object Classes Challenge , 2005, MLCW.

[23]  Ivan Laptev,et al.  Improvements of Object Detection Using Boosted Histograms , 2006, BMVC.

[24]  Frédéric Jurie,et al.  Latent mixture vocabularies for object categorization and segmentation , 2006, Image Vis. Comput..

[25]  Bernt Schiele,et al.  Multiple Object Class Detection with a Generative Model , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[26]  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).

[27]  Andrew Zisserman,et al.  An Exemplar Model for Learning Object Classes , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[28]  Cordelia Schmid,et al.  Accurate Object Detection with Deformable Shape Models Learnt from Images , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

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

[30]  Thomas L. Griffiths,et al.  Probabilistic Topic Models , 2007 .

[31]  Antonio Criminisi,et al.  Harvesting Image Databases from the Web , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[32]  Antonio Torralba,et al.  Sharing Visual Features for Multiclass and Multiview Object Detection , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.