Compute time for a typical ConvNet (as seen in Figure 3.1) ,
Quantization effect on trained networks: the x axis shows the fixed point position, the y axis the percentage of weights being zeroed after quantization A two-tier approach for arabic offline handwriting recognition, IWFHR'06, 2006. ,
A computation model with data flow sequencing, p.66, 1969. ,
Data Memory Minimisation For Synchronous Data Flow Graphs Emulated On DSP-FPGA Targets, Proceedings of the 34th Design Automation Conference, pp.64-69, 1997. ,
DOI : 10.1109/DAC.1997.597118
Training Hierarchical Feed-Forward Visual Recognition Models Using Transfer Learning from Pseudo-Tasks, ECCV, p.62, 2008. ,
DOI : 10.1007/978-3-540-88690-7_6
Tile processor: Embedded multicore for networking and multimedia. Hotchips, p.21, 2007. ,
Contour Detection and Hierarchical Image Segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.33, issue.5, pp.898-916, 2011. ,
DOI : 10.1109/TPAMI.2010.161
Greedy layer-wise training of deep networks, NIPS, p.62, 2007. ,
Shape Matching and Object Recognition Using Low Distortion Correspondences, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), 2005. ,
DOI : 10.1109/CVPR.2005.320
Software synthesis from dataflow graphs Synthesis of embedded software from synchronous dataflow specifications Journal of VLSI signal processing systems for signal, image and video technology, pp.151-166, 1996. ,
Online algorithms and stochastic approximations, Online Learning and Neural Networks, p.12, 1998. ,
Large-scale machine learning with stochastic gradient descent, Proceedings of the 19th International Conference on Computational Statistics (COMPSTAT'2010), pp.177-187, 2010. ,
Large scale online learning, Advances in Neural Information Processing Systems, p.12, 2004. ,
Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001, pp.105-112, 2001. ,
DOI : 10.1109/ICCV.2001.937505
An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.26, issue.9, pp.1124-1137, 2004. ,
DOI : 10.1109/TPAMI.2004.60
Fast approximate energy minimization via graph cuts, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.23, issue.11, pp.1222-1239, 2001. ,
DOI : 10.1109/34.969114
A new radical based approach to offline handwritten east-asian character recognition, IWFHR. 8, 2006. ,
URL : https://hal.archives-ouvertes.fr/inria-00112634
High performance convolutional neural networks for document processing, IWFHR. 8, 2006. ,
URL : https://hal.archives-ouvertes.fr/inria-00112631
Optimally combining a cascade of classifiers, Proc. of Document Recognition and Retrieval 13, Electronic Imaging, 2006. ,
A committee of neural networks for traffic sign classification, The 2011 International Joint Conference on Neural Networks, p.45, 1918. ,
DOI : 10.1109/IJCNN.2011.6033458
Scalable learning for object detection with GPU hardware, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp.4287-4293, 2009. ,
DOI : 10.1109/IROS.2009.5354084
Torch. presented at the Workshop on Machine Learning Open Source Software, p.76, 2008. ,
Deep learning for efficient discriminative parsing, VideoLectures .net, vol.7, pp.45-48, 2011. ,
Building heterogeneous platforms for end-to-end online learning based on dataflow computing design, p.78, 2010. ,
Causal graph-based video segmentation, 2013 IEEE International Conference on Image Processing, p.88, 2013. ,
DOI : 10.1109/ICIP.2013.6738875
URL : https://hal.archives-ouvertes.fr/hal-00830820
Indoor semantic segmentation using depth information, Proceedings of the International Conference on Learning Representations, 2013. ,
URL : https://hal.archives-ouvertes.fr/hal-00805105
Histograms of Oriented Gradients for Human Detection, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), p.65, 2005. ,
DOI : 10.1109/CVPR.2005.177
URL : https://hal.archives-ouvertes.fr/inria-00548512
Text detection with convolutional neural networks, International Conference on Computer Vision Theory and Applications, 2008. ,
A preliminary architecture for a basic data-flow processor Cnp: An fpgabased processor for convolutional networks, SIGARCH Comput. Archit. News International Conference on Field Programmable Logic and Applications, pp.126-132, 1974. ,
Hardware accelerated convolutional neural networks for synthetic vision systems, Proceedings of 2010 IEEE International Symposium on Circuits and Systems, pp.48-66, 2010. ,
DOI : 10.1109/ISCAS.2010.5537908
Neuflow: A runtime reconfigurable dataflow processor for vision, Proceedings of the Fifth IEEE Workshop on Embedded Computer Vision, p.49, 2011. ,
Scene parsing with multiscale feature learning, purity trees, and optimal covers, Proceedings of the International Conference on Machine Learning (ICML), p.38, 2012. ,
URL : https://hal.archives-ouvertes.fr/hal-00715469
Efficient Graph-Based Image Segmentation, International Journal of Computer Vision, vol.59, issue.2, pp.167-181, 2004. ,
DOI : 10.1023/B:VISI.0000022288.19776.77
A simple algorithm for finding maximal network flows and an application to the Hitchcock problem, Journal canadien de math??matiques, vol.9, issue.0, p.46, 1955. ,
DOI : 10.4153/CJM-1957-024-0
Large-scale privacy protection in street-level imagery, ICCV'09, 2009. ,
Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position, Pattern Recognition, vol.15, issue.6, pp.455-469, 1982. ,
DOI : 10.1016/0031-3203(82)90024-3
Class segmentation and object localization with superpixel neighborhoods, 2009 IEEE 12th International Conference on Computer Vision, pp.670-677, 2009. ,
DOI : 10.1109/ICCV.2009.5459175
Convolutional face finder: a neural architecture for fast and robust face detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.26, issue.11, 2004. ,
DOI : 10.1109/TPAMI.2004.97
Decomposing a scene into geometric and semantically consistent regions, 2009 IEEE 12th International Conference on Computer Vision, pp.1-8, 2009. ,
DOI : 10.1109/ICCV.2009.5459211
Dimensionality Reduction by Learning an Invariant Mapping, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Volume 2 (CVPR'06), p.47, 2006. ,
DOI : 10.1109/CVPR.2006.100
Learning long-range vision for autonomous off-road driving, Journal of Field Robotics, vol.23, issue.9, pp.120-144, 2009. ,
DOI : 10.1002/rob.20276
Using Learned Features from 3D Data for Robot Navigation, 2007. ,
DOI : 10.1007/978-3-540-73424-6_8
Performance Studies of Id on the Monsoon Dataflow System, Journal of Parallel and Distributed Computing, vol.18, issue.3, p.69, 1993. ,
DOI : 10.1006/jpdc.1993.1065
Reducing the Dimensionality of Data with Neural Networks, Science, vol.313, issue.5786, p.62, 2006. ,
DOI : 10.1126/science.1127647
Large-scale learning with svm and convolutional nets for generic object categorization, Proc. Computer Vision and Pattern Recognition Conference (CVPR'06, p.57, 2006. ,
Natural image denoising with convolutional networks, Advances in Neural Information Processing Systems, 2008. ,
Supervised Learning of Image Restoration with Convolutional Networks, 2007 IEEE 11th International Conference on Computer Vision, 2007. ,
DOI : 10.1109/ICCV.2007.4408909
What is the best multi-stage architecture for object recognition?, 2009 IEEE 12th International Conference on Computer Vision, p.64, 2009. ,
DOI : 10.1109/ICCV.2009.5459469
Fast inference in sparse coding algorithms with applications to object recognition, p.62, 2008. ,
Learning invariant features through topographic filter maps, 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp.51-61, 2009. ,
DOI : 10.1109/CVPR.2009.5206545
Learning convolutional feature hierachies for visual recognition, Advances in Neural Information Processing Systems, p.51, 2010. ,
On the shortest spanning subtree of a graph and the traveling salesman problem, Proceedings of the AMS, pp.48-50, 1956. ,
DOI : 10.1090/S0002-9939-1956-0078686-7
Efficiently selecting regions for scene understanding, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.3217-3224, 2010. ,
DOI : 10.1109/CVPR.2010.5540072
Why systolic architectures?, Computer, vol.15, issue.1, pp.300-309, 1986. ,
DOI : 10.1109/MC.1982.1653825
Stream data types for signal processing, Advances in Dataflow Architecture and Multithreading, p.76, 1994. ,
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Volume 2 (CVPR'06), pp.2169-2178, 2006. ,
DOI : 10.1109/CVPR.2006.68
URL : https://hal.archives-ouvertes.fr/inria-00548585
Lush reference manual. Tech. rep, 1998. ,
Backpropagation Applied to Handwritten Zip Code Recognition, Neural Computation, vol.1, issue.4, p.61, 1989. ,
DOI : 10.1007/BF00133697
Handwritten digit recognition with a back-propagation network, NIPS'89 . 5, p.59, 1990. ,
Gradient-based learning applied to document recognition, Proceedings of the IEEE, pp.2278-2324, 1998. ,
DOI : 10.1109/5.726791
Off-road obstacle avoidance through end-to-end learning, Advances in Neural Information Processing Systems (NIPS 2005), 2005. ,
Static Scheduling of Synchronous Data Flow Programs for Digital Signal Processing, IEEE Transactions on Computers, vol.36, issue.1, pp.24-35, 1987. ,
DOI : 10.1109/TC.1987.5009446
Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations, Proceedings of the 26th Annual International Conference on Machine Learning, ICML '09, p.62, 2009. ,
DOI : 10.1145/1553374.1553453
A pylon model for semantic segmentation Nvidia tesla: A unified graphics and computing architecture, Advances in Neural Information Processing Systems, pp.47-71, 2008. ,
Nonparametric scene parsing: Label transfer via dense scene alignment, Artificial Intelligence, vol.41, p.42, 2009. ,
Distinctive Image Features from Scale-Invariant Keypoints, International Journal of Computer Vision, vol.60, issue.2, p.65, 2004. ,
DOI : 10.1023/B:VISI.0000029664.99615.94
Nonlinear image representation using divisive normalization, CVPR, p.61, 2008. ,
The Perception of Multiple Objects, A Connectionist Approach, 1991. ,
Stacked Hierarchical Labeling, p.42, 2010. ,
DOI : 10.1007/978-3-642-15567-3_5
Multiclass Object Recognition with Sparse, Localized Features, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Volume 1 (CVPR'06), p.57, 2006. ,
DOI : 10.1109/CVPR.2006.200
Geodesic saliency of watershed contours and hierarchical segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.18, issue.12, pp.1163-1173, 1996. ,
DOI : 10.1109/34.546254
URL : https://hal.archives-ouvertes.fr/hal-00622128
Playing with Kruskal: Algorithms for Morphological Trees in Edge-Weighted Graphs, International Symposium on Mathematical Morphology, pp.135-146, 2013. ,
DOI : 10.1007/978-3-642-38294-9_12
URL : https://hal.archives-ouvertes.fr/hal-00798621
Face Detection Using GPU-Based Convolutional Neural Networks, 2009. ,
DOI : 10.1007/978-3-642-03767-2_10
Toward automatic phenotyping of developing embryos from REFERENCES videos, IEEE Trans. on Image Processing, special issue on Molecular & Cellular Bioimaging, issue.9, 2005. ,
A convolutional neural network hand tracker, Neural Information Processing Systems, pp.901-908, 1995. ,
Sparse coding with an overcomplete basis set: a strategy employed by v1? Vision Research, p.62, 1997. ,
Synergistic Face Detection and Pose Estimation with Energy-Based Models, Journal of Machine Learning Research, vol.8, issue.8, pp.1197-1215, 2007. ,
DOI : 10.1007/11957959_10
Extended synchronous dataflow for efficient dsp system prototyping. Design Automation for Embedded Systems, pp.295-322, 2002. ,
Dataflow vision processing system-on-a-chip, IEEE International Midwest Symposium on Circuits and systems ,
Why is Real-World Visual Object Recognition Hard?, PLoS Computational Biology, vol.58, issue.1, pp.27-32, 2008. ,
DOI : 10.1371/journal.pcbi.0040027.sg004
Sparse feature learning for deep belief networks, NIPS'07, p.64, 2007. ,
Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition, 2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007. ,
DOI : 10.1109/CVPR.2007.383157
LabelMe: A Database and Web-Based Tool for Image Annotation, International Journal of Computer Vision, vol.3, issue.1, pp.79-92, 2007. ,
DOI : 10.1007/s11263-007-0090-8
Object Recognition with Features Inspired by Visual Cortex, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), p.58, 2005. ,
DOI : 10.1109/CVPR.2005.254
TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation, Lecture Notes in Computer Science, vol.3951, issue.1, pp.1-15, 2006. ,
DOI : 10.1007/11744023_1
Best practices for convolutional neural networks applied to visual document analysis, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings., pp.958-962, 2003. ,
DOI : 10.1109/ICDAR.2003.1227801
Best practices for convolutional neural networks applied to visual document analysis, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings., p.61, 2003. ,
DOI : 10.1109/ICDAR.2003.1227801
Parsing Natural Scenes and Natural Language with Recursive Neural Networks, Proceedings of the 26th International Conference on Machine Learning (ICML, p.42, 2011. ,
Superparsing, International Journal of Computer Vision, vol.30, issue.11, pp.352-365, 2010. ,
DOI : 10.1007/s11263-012-0574-z
Unbiased look at dataset bias, CVPR 2011, pp.1521-1528, 2011. ,
DOI : 10.1109/CVPR.2011.5995347
Maximin affinity learning of image segmentation, NIPS, vol.17, p.51, 2009. ,
Original approach for the localisation of objects in images, IEE Proceedings - Vision, Image, and Signal Processing, vol.141, issue.4, pp.245-250, 1994. ,
DOI : 10.1049/ip-vis:19941301
Extracting and composing robust features with denoising autoencoders, Proceedings of the 25th international conference on Machine learning, ICML '08, 2008. ,
DOI : 10.1145/1390156.1390294
Deep learning via semisupervised embedding, p.62, 2008. ,
Learning Hierarchical Features for Scene Labeling, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013. ,
Comparison between Frame-Constrained Fix-Pixel-Value and Frame-Free Spiking-Dynamic-Pixel ConvNets for Visual Processing, Frontiers in Neuroscience, 2012. ,
DOI : 10.3389/fnins.2012.00032
Large-Scale FPGA-Based Convolutional Networks, Scaling Up Machine Learning, 2011. ,
DOI : 10.1017/CBO9781139042918.020
Visual Tracking and LIDAR Relative Positioning for Automated Launch and Recovery of an Unmanned Rotorcraft from Ships at Sea, Naval Engineers Journal, vol.121, issue.No. 3, pp.99-110, 2009. ,
DOI : 10.1111/j.1559-3584.2009.00194.x
Indoor Semantic Segmentation using depth information, Proceedings of the International Conference on Learning Representations, 2013. ,
Clustering Learning for Robotic Vision, Proceedings of the International Conference on Learning Representations, 2013. ,
NeuFlow: Dataflow Vision Processing System-on-a-Chip, IEEE International Midwest Symposium on Circuits and systems, 2012. ,
NeuFlow: A runtime reconfigurable dataflow processor for vision, CVPR 2011 WORKSHOPS, 2011. ,
DOI : 10.1109/CVPRW.2011.5981829
Hardware accelerated convolutional neural networks for synthetic vision systems, Proceedings of 2010 IEEE International Symposium on Circuits and Systems, 2010. ,
DOI : 10.1109/ISCAS.2010.5537908
Convolutional networks and applications in vision, Proceedings of 2010 IEEE International Symposium on Circuits and Systems, 2010. ,
DOI : 10.1109/ISCAS.2010.5537907
An FPGA-based stream processor for embedded real-time vision with Convolutional Networks, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops ,
DOI : 10.1109/ICCVW.2009.5457611
CNP: An FPGAbased Processor for Convolutional Networks, International Conference on Field Programmable Logic and Applications (FPL'09, 2009. ,
Visual Tracking and LIDAR Relative Positioning for Automated Launch and Recovery of an Unmanned Rotorcraft from Ships at Sea, ASNE Conference on Launch and Recovery of Manned and Unmanned Vehicles From Surface Platforms, 2008. ,
DOI : 10.1111/j.1559-3584.2009.00194.x
Invited talk at the Rowland Institute at Harvard (David Cox's lab), 2012. ,
Gave a series of lectures (tutorials) on deeplearning and feature learning, at the IPAM Graduate Summer School, 2012. ,
A Dataflow Processor for General Purpose Vision, presented at Neural Information Processing Systems (NIPS10), 2010. ,
Building Heterogeneous Platforms for End-to-end Online Learning Based on Dataflow Computing Design, Workshop on Learning on Cores, Clusters and Clouds (LCCC @ NIPS10), 2010. ,
A Study of Parallel Computing for Machine Learning: Which Platform for Which Application, presented at the 4th Annual Machine Learning Symposium at the New York Academy of Sciences, 2010. ,
NeuFlow: a Vision Processor for Real-Time Object Categorization in Megapixel Videos ,
NeuFlow: a Dataflow Computer for General Purpose Vision " , presented at e-labs Seminar Series, 2010. ,
Bio-Inspired Processing for Ultra-Fast Object Categorization, High Performance Embedded Computing (HPEC10), 2010. ,
CNP: An FPGA-based processor for Convolutional Networks, 2009 International Conference on Field Programmable Logic and Applications, 2009. ,
DOI : 10.1109/FPL.2009.5272559
Hardware Implementation of a Convolutional Neural Network ? Design of a Neural Processor, 2008. ,
Cartography of a Wall in a Coke Oven by Reconstruction of a Panoramic Picture, 2008. ,
Implementation of a Tracking System within a FPGA, 2007. ,
Torch7: A Matlablike Environment for Machines Learning, Big Learning Workshop (@ NIPS'11) Runtime Reconfigurable Dataflow Processor, p.742, 2011. ,