Universität Bonn: Autonomous Intelligent Systems Group   Computer Science Institute VI: Autonomous Intelligent Systems

Data Sets

Pascal VOC 2010 superpixel graphs

The Pascal VOC dataset is a standard benchmark for object class segmentation. Here we provide preprocessed data for use with the PyStruct structured prediction library. It consists of potentials derived from Philipp Krähenbühl's Textonboost implementation, superpixels computed with SLIC and superpixel connectivity graphs.

Downloads: Training set Validation set


LabelMe-12-50K Data Set

LabelMe-12-50K

The LabelMe-12-50k data set contains 50.000 images of centered objects from 12 categories, which have been extracted from LabelMe.

For a description of the data set and for download go here


Source Code

CUV Library

Local-Impact RMB

The CUV Library is a C++ framework for easy use of Nvidia CUDA functions on matrices. It contains basic matrix operations and convolutions which can be performed both on the CPU or the GPU. The library also contains python binding so that all functionality can be used in python for fast prototyping.

The CUV Library can be downloaded at http://github.com/deeplearningais/CUV

We also provide a tutorial on an a simple MLP that learns MNIST to get you started with CUV.

API Documentation is included, but can also be viewed online.

CURFIL: CUDA Random Forests for Image Labeling

Object Class Segmentation with CURFIL

An open source implementation with NVIDIA CUDA™ that accelerates random forest training and prediction for image labeling by using the massive parallel computing power offered by GPUs. 

Github link: https://github.com/deeplearningais/curfil

Universität Bonn, Institute for Computer Science, Departments: I, II, III, IV, V, VI