Alexey Dosovitskiy

Chair of Pattern Recognition and Image Processing
Department of Computer Science
Albert-Ludwigs-University
Georges-Koehler-Allee 052, room 01-019
D-79110 Freiburg i.Br., Germany

Telefon:

+49-(0)761-203-97630

Fax:

+49-(0)761-203-8262

Email:

General information

Publications

Code

NEW: Generating Images with Perceptual Similarity Metrics based on Deep Networks

v0.5:      Testing and training code
Custom caffe version (for training):      https://github.com/dosovits/caffe-fr-chairs (deepsim branch)

v0:      Trained models for layers pool5-fc8 and a python demo        Trained models for layers norm1-conv4

A. Dosovitskiy, T. Brox
Generating Images with Perceptual Similarity Metrics based on Deep Networks,
Advances in Neural Information Processing Systems (NIPS), 2016.

Inverting Visual Representations with Convolutional Networks

Code and examples for new Caffe version (2016):	training config and a trained model for reconstruction from FC6
	To be used with this Caffe https://github.com/dosovits/caffe-fr-chairs
Download modified Caffe used in the paper:	modified Caffe + brief readme
Download trained models from the paper:	conv1 conv2 conv3 conv4 conv5 fc6 fc7 fc8 caffenet

A. Dosovitskiy and T. Brox
Inverting Visual Representations with Convolutional Networks,
IEEE Conference in Computer Vision and Pattern Recognition (CVPR), 2016.

Learning to Generate Chairs with Convolutional Neural Networks

New version in new Caffe (2016)	trained model, demo, training example
	To be used with this Caffe https://github.com/dosovits/caffe-fr-chairs
Version used for the CVPR paper	modified Caffe + models + matlab scripts trained model training data

A. Dosovitskiy, J. T. Springenberg and T. Brox
Learning to Generate Chairs with Convolutional Neural Networks,
IEEE Conference in Computer Vision and Pattern Recognition (CVPR), 2015.

FlowNet: Learning Optical Flow with Convolutional Networks

Download modified master branch Caffe with model included: Modified Caffe + brief readme
Note: This is pre-release (v0.1) which for now only includes the model for FlowNetS, but not for FlowNetC
We will update this as soon as the correlation model is available.
Please read the included FLOWNET-README.md file.

A. Dosovitskiy and P. Fischer and E. Ilg and P. Häusser and C. Hazirbas and V. Golkov and P. v.d. Smagt and D. Cremers and T. Brox
FlowNet: Learning Optical Flow with Convolutional Networks,
IEEE International Conference on Computer Vision (ICCV), 2015.

Exemplar Convolutional Neural Networks

Download Code for Linux

A. Dosovitskiy, J. T. Springenberg, M. Riedmiller and T. Brox
Discriminative Unsupervised Feature Learning with Convolutional Neural Networks,
Advances in Neural Information Processing Systems 27 (NIPS), 2014.

A. Dosovitskiy, P.Fischer, J. T. Springenberg, M. Riedmiller and T. Brox
Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks,
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2015.