Home
Uni-Logo
 

Datasets

Binaries/Code Datasets Open Source Software

Freiburg-Berkeley Motion Segmentation Dataset
Video Segmentation Benchmark
Image Sequences
TEM Dataset
TILDA Textile Texture Database
Training data for Exemplar CNN
Generated Matching Dataset
Training data for chair generation
Stereo Ego-motion Dataset
Optical Flow Datasets: "Flying Chairs", "ChairsSDHom"
Scene Flow Datasets
Human Part Segmentation Datasets  
Rendered Handpose Dataset
Pedestrian Zone Scene


Training Data for Exemplar CNN

Terms of use

We provide some of the data we used for training ConvNets in our papers "Discriminative Unsupervised Feature Learning with Convolutional Neural Networks" and "Descriptor Matching with Convolutional Neural Networks: a Comparison to SIFT".

The datasets are provided for research purposes only and without any warranty. Any commercial use is prohibited. If you use one of the datasets in your research, you should cite the corresponding aforementioned paper.

Data used in "Discriminative Unsupervised Feature Learning with Convolutional Neural Networks": matlab  leveldb
Data used in "Descriptor Matching with Convolutional Neural Networks: a Comparison to SIFT": matlab