Search For:

Displaying 1-14 out of 14 total
Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Marc'Aurelio Ranzato, Fu Jie Huang, Y-Lan Boureau, Yann LeCun
Issue Date:June 2007
pp. 1-8
We present an unsupervised method for learning a hierarchy of sparse feature detectors that are invariant to small shifts and distortions. The resulting feature extractor consists of multiple convolution filters, followed by a feature-pooling layer that co...
 
Learning Hierarchical Features for Scene Labeling
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Clement Farabet,Camille Couprie,Laurent Najman,Yann LeCun
Issue Date:August 2013
pp. 1915-1929
Scene labeling consists of labeling each pixel in an image with the category of the object it belongs to. We propose a method that uses a multiscale convolutional network trained from raw pixels to extract dense feature vectors that encode regions of multi...
 
Dimensionality Reduction by Learning an Invariant Mapping
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Raia Hadsell, Sumit Chopra, Yann LeCun
Issue Date:June 2006
pp. 1735-1742
Dimensionality reduction involves mapping a set of high dimensional input points onto a low dimensional manifold so that 'similar
 
Large-scale Learning with SVM and Convolutional for Generic Object Categorization
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Fu Jie Huang, Yann LeCun
Issue Date:June 2006
pp. 284-291
<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...
 
Learning a Similarity Metric Discriminatively, with Application to Face Verification
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Sumit Chopra, Raia Hadsell, Yann LeCun
Issue Date:June 2005
pp. 539-546
We present a method for training a similarity metric from data. The method can be used for recognition or verification applications where the number of categories is very large and not known during training, and where the number of training samples for a s...
 
Efficient Conversion of Digital Documents to Multilayer Raster Formats
Found in: Document Analysis and Recognition, International Conference on
By Léon Bottou,Patrick Haffner,Yann LeCun
Issue Date:September 2001
pp. 0444
Abstract: How can we turn the description of a digital (i.e. electronically produced) document into something efficient for multilayer raster formats [1, 6, 4]? It is first shown that a foreground/background segmentation without overlapping foreground comp...
 
Concerto for violin and Markov model: technical perspective
Found in: Communications of the ACM
By Juan Bello, Robert Rowe, Robert Rowe, Yann LeCun, Yann LeCun
Issue Date:March 2011
pp. 86-86
The advent of multicore processors as the standard computing platform will force major changes in software design.
     
Ask the locals: Multi-way local pooling for image recognition
Found in: Computer Vision, IEEE International Conference on
By Y-Lan Boureau,Nicolas Le Roux,Francis Bach,Jean Ponce,Yann LeCun
Issue Date:November 2011
pp. 2651-2658
Invariant representations in object recognition systems are generally obtained by pooling feature vectors over spatially local neighborhoods. But pooling is not local in the feature vector space, so that widely dissimilar features may be pooled together if...
 
Learning mid-level features for recognition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Y-Lan Boureau, Francis Bach, Yann LeCun, Jean Ponce
Issue Date:June 2010
pp. 2559-2566
Many successful models for scene or object recognition transform low-level descriptors (such as Gabor filter responses, or SIFT descriptors) into richer representations of intermediate complexity. This process can often be broken down into two steps: (1) a...
 
Learning Methods for Generic Object Recognition with Invariance to Pose and Lighting
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yann LeCun, Fu Jie Huang, Léon Bottou
Issue Date:July 2004
pp. 97-104
We assess the applicability of several popular learning methods for the problem of recognizing generic visual categories with invariance to pose, lighting, and surrounding clutter. A large dataset comprising stereo image pairs of 50 uniform-colored toys un...
 
DjVu: Analyzing and Compressing Scanned Documents for Internet Distribution
Found in: Document Analysis and Recognition, International Conference on
By Patrick Haffner, Léon Bottou, Paul G. Howard, Yann LeCun
Issue Date:September 1999
pp. 625
DjVu is an image compression technique specifically geared towards the compression of scanned documents in color at high resolution. Typical magazine pages in color scanned at 300dpi are compressed to between 40 and 80 KB, or 5 to 10 times smaller than wit...
 
Pedestrian Detection with Unsupervised Multi-stage Feature Learning
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Pierre Sermanet,Koray Kavukcuoglu,Soumith Chintala,Yann Lecun
Issue Date:June 2013
pp. 3626-3633
Pedestrian detection is a problem of considerable practical interest. Adding to the list of successful applications of deep learning methods to vision, we report state-of-the-art and competitive results on all major pedestrian datasets with a convolutional...
 
Workshop summary: Workshop on learning feature hierarchies
Found in: Proceedings of the 26th Annual International Conference on Machine Learning (ICML '09)
By Geoff Hinton, Kay Yu, Ruslan Salakhutdinov, Yann LeCun, Yoshua Bengio
Issue Date:June 2009
pp. 1-1
Previous studies of Non-Parametric Kernel (NPK) learning usually reduce to solving some Semi-Definite Programming (SDP) problem by a standard SDP solver. However, time complexity of standard interior-point SDP solvers could be as high as O(n6.5). Such inte...
     
Discovering the hidden structure of house prices with a non-parametric latent manifold model
Found in: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining (KDD '07)
By Andrew Caplin, John Leahy, Sumit Chopra, Trivikraman Thampy, Yann LeCun
Issue Date:August 2007
pp. 173-182
In many regression problems, the variable to be predicted depends not only on a sample-specific feature vector, but also on an unknown (latent) manifold that must satisfy known constraints. An example is house prices, which depend on the characteristics of...
     
 1