This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication

Year(s) from:  to 
Keywords (separated by spaces):

Deformation-aware Log-Linear Models

T. Gass, T. Deselaers, and H. Ney
Deutsche Arbeitsgemeinschaft für Mustererkennung Symposium (DAGM


Abstract. 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.

Download in pdf format
  author = {T. Gass and T. Deselaers and and H. Ney},
  title = {Deformation-aware Log-Linear Models},
  booktitle = {Deutsche Arbeitsgemeinschaft für Mustererkennung Symposium (DAGM},
  year = {2009},
  publisher = {Springer},
  keywords = {LNCS}