Training Invariant Support Vector Machines
Machine Learning
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Maximum Entropy and Gaussian Models for Image Object Recognition
Proceedings of the 24th DAGM Symposium on Pattern Recognition
Best Practices for Convolutional Neural Networks Applied to Visual Document Analysis
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Adaptation in Statistical Pattern Recognition Using Tangent Vectors
IEEE Transactions on Pattern Analysis and Machine Intelligence
A fast learning algorithm for deep belief nets
Neural Computation
A Survey of Elastic Matching Techniques for Handwritten Character Recognition
IEICE - Transactions on Information and Systems
Deformation Models for Image Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hidden Conditional Random Fields
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
In this paper, we present a novel deformation-aware discriminative model for handwritten digit recognition. Unlike previous approaches our model directly considers image deformations and allows discriminative training of all parameters, including those accounting for non-linear transformations of the image. This is achieved by extending a log-linear framework to incorporate a latent deformation variable. The resulting model has an order of magnitude less parameters than competing approaches to handling image deformations. We tune and evaluate our approach on the USPS task and show its generalization capabilities by applying the tuned model to the MNIST task. We gain interesting insights and achieve highly competitive results on both tasks.