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

Deep Learning Publications


2017

Max Schwarz, Anton Milan, Arul Selvam Periyasamy, and Sven Behnke:
RGB-D Object Detection and Semantic Segmentation for Autonomous Manipulation in Clutter
Accepted for International Journal of Robotics Research (IJRR), Sage Publications, to apprear 2017.

Max Schwarz and Sven Behnke:
Data-efficient Deep Learning for RGB-D Object Perception in Cluttered Bin Picking
Accepted for Warehouse Picking Automation Workshop (WPAW), IEEE International Conference on Robotics and Automation (ICRA), Singapore, May 2017.

Jörg Wagner, Volker Fischer, Michael Herman, and Sven Behnke:
Learning Semantic Prediction using Pretrained Deep Feedforward Networks
In Proceedings of 25th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), Bruges, Belgium, April 2017.

Mircea Serban Pavel, Hannes Schulz, and Sven Behnke:
Object class segmentation of RGB-D video using recurrent convolutional neural networks
Neural Networks, Elsevier, available online January 2017.

Hannes Schulz:
Learning Object Recognition and Object Class Segmentation with Deep Neural Networks on GPU
Dissertation, Mathematisch-Naturwissenschaftliche Fakultät, Universität Bonn, 2017.

2016

German Martin Garcia, Farzad Husain, Hannes Schulz, Simone Frintrop, Carme Torras, and Sven Behnke:
Semantic Segmentation Priors for Object Discovery
In Proceedings of: 23rd International Conference on Pattern Recognition (ICPR), Cancun, Mexico, December 2016.

Farzad Husain, Hannes Schulz, Babette Dellen, Carme Torras, and Sven Behnke:
Combining Semantic and Geometric Features for Object Class Segmentation of Indoor Scenes
IEEE Robotics and Automation Letters (RA-L) 2(1):49-55, 2016.
Presented at IEEE International Conference on Robotics and Automation (ICRA), Stockholm, Sweden, May 2016.

Jörg Wagner, Volker Fischer, Michael Herman, and Sven Behnke:
Multispectral Pedestrian Detection using Deep Fusion Convolutional Neural Networks
In Proceedings of 24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), Bruges, Belgium, April 2016.

Hannes Schulz, Benedikt Waldvogel, Rasha Sheikh, and Sven Behnke:
CURFIL: A GPU Library for Image Labeling with Random Forests
In: Computer Vision, Imaging and Computer Graphics Theory and Applications, volume 598 or Communications in Computer and Information Science, pp. 416-432, Springer, 2016.

2015

Jörg Stückler, Benedikt Waldvogel, Hannes Schulz, and Sven Behnke:
Dense Real-Time Mapping of Object-Class Semantics from RGB-D Video
Journal of Real-Time Image Processing 10(4):599-609, Springer, 2015.

Mircea Serban Pavel, Hannes Schulz and Sven Behnke:
Recurrent Convolutional Neural Networks for Object-Class Segmentation of RGB-D Video
In Proceedings of International Joint Conference on Neural Networks (IJCNN), Killarney, Ireland, July 2015

Max Schwarz, Hannes Schulz, and Sven Behnke:
RGB-D Object Recognition and Pose Estimation based on Pre-trained Convolutional Neural Network Features
In Proceedings of IEEE International Conference on Robotics and Automation (ICRA), Seattle, USA, May 2015.

Hannes Schulz, Nico Höft, and Sven Behnke:
Depth and Height Aware Semantic RGB-D Perception with Convolutional Neural Networks
In Proceedings of European Symposium on Artificial Neural Networks (ESANN), April 2015.

Hannes Schulz, Benedikt Waldvogel, Rasha Sheikh, and Sven Behnke:
CURFIL: Random Forests for Image Labeling on GPU
In Proceedings of 10th International Conference on Computer Vision Theory and Applications (VISAPP), March 2015.
[Source code]

Hannes Schulz, Kyunghyun Cho, Tapani Raiko, and Sven Behnke:
Two-Layer Contractive Encodings for Learning Stable Nonlinear Features
Neural Networks  64:4-11, Elsevier, 2015.

2014

Nico Höft, Hannes Schulz and Sven Behnke:
Fast Semantic Segmentation of RGB-D Scenes with GPU-Accelerated Deep Neural Networks
In Proceedings of 37th German Conference on Artificial Intelligence (KI), pp. 80-85, Springer LNCS 8736, Stuttgart, September 2014.

Hannes Schulz and Sven Behnke:
Structured Prediction for Object Detection in Deep Neural Networks
In Proceedings of 24th International Conference on Artificial Neural Networks (ICANN), Hamburg, September 2014.

2013

Hannes Schulz, Kyunghyun Cho, Tapani Raiko, and Sven Behnke:
Two-Layer Contractive Encodings with Shortcuts for Semi-supervised Learning
In Proceedings of 20th International Conference on Neural Information Processing (ICONIP), pp. 450-457, Daegu, Korea, November 2013.

2012

    Hannes Schulz and Sven Behnke:
    Learning Two-Layer Contractive Encodings
    In Proceedings of International Conference on Artificial Neural Networks (ICANN), pp. 620-628, September 2012.

    Hannes Schulz and Sven Behnke:
    Deep Learning - Layer-wise Learning of Feature Hierarchies
    KI - Künstliche Intelligenz, 26(4): pp. 357-363, November 2012.

    Hannes Schulz and Sven Behnke:
    Learning Object-Class Segmentation with Convolutional Neural Networks
    In Proceedings of the 11th European Symposium on Artificial Neural Networks (ESANN), Bruges, Belgium, April 2012.

2011

Andreas Müller and Sven Behnke:
Multi-Instance Methods for Partially Supervised Image Segmentation
In Proceedings of First IAPR Workshop on Partially Supervised Learning (PSL), Ulm, September 2011.

Hannes Schulz and Sven Behnke:
Object-Class Segmentation using Deep Convolutional Neural Networks
DAGM Workshop on New Challenges in Neural Computation (NC2), Frankfurt, August 2011.

Hannes Schulz, Andreas Müller, and Sven Behnke:
Exploiting Local Structure in Boltzmann Machines
Neurocomputing 74(9):1411-1417, Elsevier, April 2011.

2010

Hannes Schulz, Andreas Müller, and Sven Behnke:
Investigating Convergence of Restricted Boltzmann Machine Learning
In Proceedings of NIPS Workshop on Deep Learning and Unsupervised Feature Learning, Whistler, Canada, December 2010.

Dominik Scherer, Andreas Müller, and Sven Behnke:
Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition
In Proceedings of 20th International Conference on Artificial Neural Networks (ICANN), Thessaloniki, Greece, September 2010.

Dominik Scherer, Hannes Schulz, and Sven Behnke:
Accelerating Large-Scale Convolutional Neural Networks with Parallel Graphics Multiprocessors
In Proceedings of 20th International Conference on Artificial Neural Networks (ICANN), Thessaloniki, Greece, September 2010.

Andreas Müller, Hannes Schulz, and Sven Behnke:
Topological Features in Locally Connected RBMs
In Proceedings of International Joint Conference on Neural Networks (IJCNN), July 2010.

Hannes Schulz, Andreas Müller, and Sven Behnke:
Exploiting local structure in stacked Boltzmann machines
In Proceedings of European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), Bruges, Belgium, April 2010.

2009

Dominik Scherer and Sven Behnke:
Accelerating Large-scale Convolutional Neural Networks with Parallel Graphics Multiprocessors
In Proceeding of NIPS Workshop on Large-Scale Machine Learning: Parallelism and Massive Datasets, Whistler, Canada, December 2009.

Rafael Uetz and Sven Behnke:
Locally-Connected Hierarchical Neural Networks for GPU-accelerated Object Recognition
In Proceeding of NIPS Workshop on Large-Scale Machine Learning: Parallelism and Massive Datasets, Whistler, Canada, December 2009.

Rafael Uetz and Sven Behnke:
Large-scale Object Recognition with CUDA-accelerated Hierarchical Neural Networks
In Proceedings of the 1st IEEE International Conference on Intelligent Computing and Intelligent Systems (ICIS), Shanghai, China, November 2009.

2004

Sven Behnke:
Face Localization and Tracking in the Neural Abstraction Pyramid.
Neural Computing and Applications 14(2), pp. 97-103, Jul. 2005. (online Nov. 2004).

2003

Sven Behnke:
Discovering hierarchical speech features using convolutional non-negative matrix factorization.
Proceedings of International Joint Conference on Neural Networks (IJCNN), vol. 4, pp. 2758-2763, Portland, OR, July 2003.

Sven Behnke:
A Two-Stage System for Meter Value Recognition.
In Proceedings of IEEE International Conference on Image Processing (ICIP), vol. I, pp. 549-552, Barcelona, Spain, September 2003.

Sven Behnke:
Face Localization in the Neural Abstraction Pyramid.
In Proceedings of Seventh International Conference on Knowledge-Based Intelligent Information & Engineering Systems (KES'03), Oxford, UK, LNAI 2774, vol. 2, pp. 139-145, September 2003.

Sven Behnke:
Learning Iterative Binarization using Hierarchical Recurrent Networks.
In Proceedings of Joint 13th International Conference on Artificial Neural Networks and 10th International Conference on Neural Information Processing ICANN/ICONIP 2003, Istanbul, Turkey, pp. 306-309, June 2003.

Sven Behnke:
Meter Value Recognition using Locally Connected Hierarchical Networks.
In Proceedings of 11th European Symposium on Artificial Neural Networks ESANN'03 -- Bruges, Belgium, pp. 535-540, 2003.

Sven Behnke:
Hierarchical Neural Networks for Image Interpretation.
Lecture Notes in Computer Science 2766, Springer, 2003.


2002

Sven Behnke:
Learning Face Localization Using Hierarchical Recurrent Networks.
In Proceedings of International Conference on Artificial Neural Networks (ICANN), Madrid, Spain, pp. 1319-1324, 2002.

2001

Sven Behnke:
Learning Iterative Image Reconstruction in the Neural Abstraction Pyramid.
International Journal of Computational Intelligence and Applications, Special Issue on Neural Networks at IJCAI-2001, vol. 1, no. 4, pp. 427-438, 2001. 

Sven Behnke:
Learning Iterative Image Reconstruction.
Proceedings of Seventeenth International Joint Conference on Artificial Intelligence (IJCAI), Seattle, USA, pp. 1353-1358, 2001.

1999

Sven Behnke:
Hebbian learning and competition in the Neural Abstraction Pyramid
In Proceedings of International Joint Conference on Neural Networks (IJCNN'99) -- Washington, DC, paper number #491, 1999. 

1998

Sven Behnke and Raul Rojas:
Activity Driven Update in the Neural Abstraction Pyramid
Proceedings of the 8th International Conference on Artificial Neural Networks (ICANN), Skövde, Sweden, pp 567-572, September 1998.

Sven Behnke and Raul Rojas:
Neural Abstraction Pyramid: A hierarchical image understanding architecture
In Proceedings of International Joint Conference on Neural Networks (IJCNN'98) -- Anchorage, AL, vol. 2, pp. 820-825, 1998.

 

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