Convolutional Filter Learning

Downloads

Learning Convolutional Filters

Sample code for learning convolutional filters (MATLAB)

Pixel-wise medical image segmentation leveraging ad-hoc features with learned filters

Framework for learning a filter bank and perform pixel classification (C++/MATLAB)

Learning Separable Filters

Code for learning 2D separable filters and perform classification (MATLAB/C++)
Code for learning 3D separable filters and perform classification (MATLAB/C++)
Code for learning 2D separable filters with tensor decomposition (MATLAB)
Code for learning 3D separable filters with tensor decomposition (MATLAB)

Learning Separable Filters

A. Sironi; B. Tekin; R. Rigamonti; V. Lepetit; P. Fua 

IEEE Transactions on Pattern Analysis and Machine Intelligence. 2015. Vol. 37, num. 1, p. 94-106. DOI : 10.1109/Tpami.2014.2343229.

On the Relevance of Sparsity for Image Classification

R. Rigamonti; V. Lepetit; G. González; E. Türetken; F. Benmansour et al. 

Computer Vision and Image Understanding. 2014. Vol. 125, p. 115-127. DOI : 10.1016/j.cviu.2014.03.009.

Accurate and Efficient Linear Structure Segmentation by Leveraging Ad Hoc Features with Learned Filters

R. Rigamonti; V. Lepetit 

2012. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Nice, France, October 1-5, 2012. p. 189-197. DOI : 10.1007/978-3-642-33415-3_24.

Are Sparse Representations Really Relevant for Image Classification?

R. Rigamonti; M. Brown; V. Lepetit 

2011. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2011), Colorado Springs, p. 1545-1552.

Filter Learning for Linear Structure Segmentation

R. Rigamonti; E. Türetken; G. González Serrano; P. Fua; V. Lepetit 

2011

Contacts

Roberto Rigamonti [e-mail]
Amos Sironi [e-mail]
Vincent Lepetit [e-mail]
Pascal Fua [e-mail]

License

The code is released under the terms of the GNU General Public License (GPL), version 3.0.