Machine Learning in Computer Vision

For a robot to be truly autonomous, it must be able to learn (and infer) from sensory inputs. Possibly the most important sensor is the camera. This block seminar looks at the exciting intersection of Machine Learning and Computer Vision, which is still in its infancy. The seminar reflects current research trends.

Papers: A brief note on the following list:
denotes the main paper. denotes papers that accompany the main paper and help in comprehending it.

• A. Torralba and A. Oliva: Statistics of natural image categories, Network: Computation in Neural Systems(14), 2003.
• A. Torralba and A. Oliva: Depth estimation from image structure, IEEE Transactions on Pattern Analysis and Machine Intelligence 24(9), 2002.
• A. Oliva and A. Torralba: Modeling the shape of the scene: a holistic representation of the spatial envelope, International Journal of Computer Vision, 42(3), 2001.
• B. Olshausen and D. Field: Emergence of simple-cell receptive field properties by learning a sparse code for natural images, Nature(381), 1996.
• B. Olshausen and D. Field: Natural Image Statistics and Efficient Coding, Network: Computation in Neural Systems(7), 1996.
• B. Olshausen and D. Field: Vision and the Coding of Natural Images, American Scientist(88), 2000.
• N. N. Schraudolph, M. Eldracher, J. Schmidhuber: Processing Images by Semi-Linear Predictability Minimization , Network 10(2), 1999.
• L. Fei-Fei and P. Perona: A Bayesian hierarchical model for learning natural scene categories, Proc. CVPR 2005.
• J. Sivic, B. Russell, A. Efros, A. Zisserman, and W. Freeman: Discovering Objects and their Location in Images,, ICCV 2005.
• E. Sudderth, A. Torralba, W. Freeman and A. Willsky: Describing Visual Scenes using Transformed Objects and Parts, NIPS 2005.
• T. Hoffmann: Unsupervised Learning by Probabilistic Latent Semantic Analysis, Machine Learning 42(1-2), 2001.
• D. Blei, A. Ng and M. Jordan: Latent Dirichlet allocation, Journal of Machine Learning Research, 2003.
• R. Hadsell and S. Chopra and Y. LeCun: Dimensionality Reduction by Learning an Invariant Mapping, in Proc. of Computer Vision and Pattern Recognition Conference (CVPR 2006), 2006.
• J. Tenenbaum,V. Silva and J. Langford: A Global Geometric Framework for Nonlinear Dimensionality Reduction , Science(290), 2000.
• S. Roweis and L. Saul: Nonlinear dimensionality reduction by locally linear embedding, Science(290), 2000.
• C. Bregler and S. Omohundro: Surface learning with applications to lipreading, NIPS(6), 1994.
• W. T. Freeman and E. C. Pasztor: Learning low-level vision, International Conference on Computer Vision, 1999.
• W. Freeman, E. Pasztor and O. Carmichael: Learning low-level vision (a detailed version), International Journal of Computer Vision, 40(1), 2000.
• Y. Weiss: Interpreting images by propagating Bayesian beliefs in: M.C. Mozer, M.I. Jordan and T. Petsche: Advances in Neural Information Processing Systems (9), 1997.
• Y. Rubner, C. Tomasi, and L. Guibas: A Metric for Distributions with Applications to Image Databases, Proceedings of the 1998 IEEE International Conference on Computer Vision, Bombay, India, January 1998.
• Y. Rubner, C. Tomasi, and L. Guibas: The earth mover's distance as a metric for image retrieval, International Journal of Computer Vision, November 2000.
• J. Puzicha, Y. Rubner, C. Tomasi, J. Buhmann: Empirical Evaluation of Dissimilarity Measures for Color and Texture, IEEE International Conference on Computer Vision, Kerkyra, Greece, September 1999.
• L. Zhu, Y. Chen, A. Yuille: Unsupervised Learning of a Probabilistic Grammar for Object Detection and Parsing, Proc. NIPS, 2006.
• H. Schneiderman and T. Kanade: Object Detection Using the Statistics of Parts, International Journal of Computer Vision, 56(3), 2004.
• Viola and Jones: Robust Real-time Object Detection, International Journal of Computer Vision, 2001.
• A. Torralba, K. Murphy and W. Freeman: Sharing features: efficient boosting procedures for multiclass object detection, Proc. CVPR, Washington(D.C), 2004.
• J. Friedman,T. Hastie and R. Tibshirani: Additive Logistic Regression: a Statistical View of Boosting, Stanford University Technical Report, 1998.
• L. Fei-Fei, R. Fergus and P. Perona: One-Shot learning of object categories, IEEE Trans. PAMI, 2006
• T. Kadir and M. Brady: Scale, saliency and image description, International Journal of Computer Vision, 2001.
• R. Fergus, P. Perona and A. Zisserman: Object class recognition by unsupervised scale-invariant learning, Proc. CVPR, 2003.
• T. Serre, L. Wolf and T. Poggio: Object recognition with features inspired by visual cortex, Proc. CVPR, San Diego, June 2005
• T. Serre, L. Wolf and T. Poggio: A new biologically motivated framework for robust object recognition, CBCL Memo 243, 2004.
• T. Serre, M. Kouh, C. Cadieu, U. Knoblich, G. Kreiman and T. Poggio: A theory of object recognition: computations and circuits in the feedforward path of the ventral stream in primate visual cortex, CBCL Memo 259, 2005.

Organizer: Professor Jürgen Schmidhuber.

Contact: Christian Osendorfer. Please direct questions, suggestions, etc. regarding this seminar to Christian.

Presentation: Each student presents one (main) paper. The presentation should be about 30 - 40 minutes. The presentation language is either German or English. You might want to check out these suggestions for your presentation. Talk to your advisor at least 2 weeks before your scheduled talk and show him your presentation.

Audience: The presenter will give his talk not only to those assigning ECTS credits (or the Schein) but to the whole group. Every member of the audience should be prepared, and must have (tried to) read the respective paper at least once or twice. We expect lots of questions to be asked during or after the talks. Hopefully this will make the seminar vivid and interesting and not a dull must-sit-through event. For the same reason, the seminar will be held in (2-3) blocks after the winter break (in accordance with participants' schedules).

Composition: You also must write a summary of your talk. It should be about 10 pages. Hand it in until the end of the semester (but better finish your summary before you give your talk, because trying to write things down in your own words will help you realize which parts of the paper(s) are important).

ECTS: 4 (2SWS).

Grading: In order to get the credits (ECTS/Schein), you must give a presentation, write a summary and attend every talk (occasional exceptions to the last requirement can be made on an individual basis).

First Block:
 
Someday in January/February 2008
 
Exact time and date to be announced
 
MI 03.07.023