2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06) (2006)
New York, NY
June 17, 2006 to June 22, 2006
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CVPR.2006.164
Fu Jie Huang , New York University, New York, NY, USA
Yann LeCun , New York University, New York, NY, USA
<p>The detection and recognition of generic object categories with invariance to viewpoint, illumination, and clutter requires the combination of a feature extractor and a classifier. We show that architectures such as convolutional networks are good at learning invariant features, but not always optimal for classification, while Support Vector Machines are good at producing decision surfaces from wellbehaved feature vectors, but cannot learn complicated invariances. We present a hybrid system where a convolutional network is trained to detect and recognize generic objects, and a Gaussian-kernel SVM is trained from the features learned by the convolutional network.</p> <p>Results are given on a large generic object recognition task with six categories (human figures, four-legged animals, airplanes, trucks, cars, and "none of the above"), with multiple instances of each object category under various poses, illuminations, and backgrounds. On the test set, which contains different object instances than the training set, an SVM alone yields a 43.3% error rate, a convolutional net alone yields 7.2% and an SVM on top of features produced by the convolutional net yields 5.9%.</p>
F. J. Huang and Y. LeCun, "Large-scale Learning with SVM and Convolutional for Generic Object Categorization," 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)(CVPR), New York, NY, 2006, pp. 284-291.