Strecha C.,Ecole Polytechnique Federale de Lausanne |
Bronstein A.M.,Technion - Israel Institute of Technology |
Bronstein M.M.,Institute of Computational Science |
Fua P.,Ecole Polytechnique Federale de Lausanne
IEEE Transactions on Pattern Analysis and Machine Intelligence | Year: 2012
SIFT-like local feature descriptors are ubiquitously employed in computer vision applications such as content-based retrieval, video analysis, copy detection, object recognition, photo tourism, and 3D reconstruction. Feature descriptors can be designed to be invariant to certain classes of photometric and geometric transformations, in particular, affine and intensity scale transformations. However, real transformations that an image can undergo can only be approximately modeled in this way, and thus most descriptors are only approximately invariant in practice. Second, descriptors are usually high dimensional (e.g., SIFT is represented as a 128-dimensional vector). In large-scale retrieval and matching problems, this can pose challenges in storing and retrieving descriptor data. We map the descriptor vectors into the Hamming space in which the Hamming metric is used to compare the resulting representations. This way, we reduce the size of the descriptors by representing them as short binary strings and learn descriptor invariance from examples. We show extensive experimental validation, demonstrating the advantage of the proposed approach. © 2012 IEEE.
De Coninck A.,Ghent University |
Kourounis D.,Institute of Computational Science |
Verbosio F.,Institute of Computational Science |
Schenk O.,Institute of Computational Science |
And 3 more authors.
Proceedings - 23rd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, PDP 2015 | Year: 2015
Genomic prediction for plant breeding requires taking into account environmental effects and variations of genetic effects across environments. The latter can be modelled by estimating the effect of each genetic marker in every possible environmental condition, which leads to a huge amount of effects to be estimated. Nonetheless, the information about these effects is only sparsely present, due to the fact that plants are only tested in a limited number of environmental conditions. In contrast, the genotypes of the plants are a dense source of information and thus the estimation of both types of effects in one single step would require as well dense as sparse matrix formalisms. This paper presents a way to efficiently apply a high performance computing infrastructure for dealing with large-scale genomic prediction settings, relying on the coupling of dense and sparse matrix algebra. © 2015 IEEE.
Rietmann M.,Institute of Computational Science |
Messmer P.,Nvidia |
Nissen-Meyer T.,ETH Zurich |
Peter D.,Princeton University |
And 6 more authors.
International Conference for High Performance Computing, Networking, Storage and Analysis, SC | Year: 2012
Computational seismology is an area of wide sociological and economic impact, ranging from earthquake risk assessment to subsurface imaging and oil and gas exploration. At the core of these simulations is the modeling of wave propagation in a complex medium. Here we report on the extension of the high-order finite-element seismic wave simulation package SPECFEM3D to support the largest scale hybrid and homogeneous supercomputers. Starting from an existing highly tuned MPI code, we migrated to a CUDA version. In order to be of immediate impact to the science mission of computational seismologists, we had to port the entire production package, rather than just individual kernels. One of the challenges in parallelizing finite element codes is the potential for race conditions during the assembly phase. We therefore investigated different methods such as mesh coloring or atomic updates on the GPU. In order to achieve strong scaling, we needed to ensure good overlap of data motion at all levels, including internode and host-accelerator transfers. Finally we carefully tuned the GPU implementation. The new MPI/CUDA solver exhibits excellent scalability and achieves speedup on a node-to-node basis over the carefully tuned equivalent multi-core MPI solver. To demonstrate the performance of both the forward and adjoint functionality, we present two case studies run on the Cray XE6 CPU and Cray XK6 GPU architectures up to 896 nodes: (1) focusing on most commonly used forward simulations, we simulate seismic wave propagation generated by earthquakes in Turkey, and (2) testing the most complex seismic inversion type of the package, we use ambient seismic noise to image 3-D crust and mantle structure beneath western Europe. © 2012 IEEE.
Fang X.,Institute of Computational Science |
Liu G.,University of Electronic Science and Technology of China |
Huang T.-Z.,Institute of Computational Science
WSEAS Transactions on Systems | Year: 2010
Neural gas network is a single-layered soft competitive neural network, which can be applied to clustering analysis with fast convergent speed comparing to Self-organizing Map (SOM), K-means etc. Combining neural gas with principal component analysis, this paper proposes a new clustering method, namely principal components analysis neural gas (PCA-NG), and the online learning algorithm is also given. The soft competitive learning of PCA-NG is based on local principal subspace, which characterizes the profile of a certain cluster. We utilize the PCA-NG to the domain of intrusion detection. Some experiments are carried out to illustrate the performance of the proposed approach by using a synthetic Gaussian-distributed dataset and the KDD CUP 1999 Intrusion Detection Evaluation dataset.
Maiolo M.,University of Applied Sciences and Arts Southern Switzerland |
Maiolo M.,Institute For Angewandte Simulation |
Vancheri A.,University of Applied Sciences and Arts Southern Switzerland |
Krause R.,Institute of Computational Science |
Danani A.,University of Applied Sciences and Arts Southern Switzerland
Journal of Computational Physics | Year: 2015
In this paper, we apply Multiresolution Analysis (MRA) to develop sparse but accurate representations for the Multiscale Coarse-Graining (MSCG) approximation to the many-body potential of mean force. We rigorously framed the MSCG method into MRA so that all the instruments of this theory become available together with a multitude of new basis functions, namely the wavelets. The coarse-grained (CG) force field is hierarchically decomposed at different resolution levels enabling to choose the most appropriate wavelet family for each physical interaction without requiring an a priori knowledge of the details localization. The representation of the CG potential in this new efficient orthonormal basis leads to a compression of the signal information in few large expansion coefficients. The multiresolution property of the wavelet transform allows to isolate and remove the noise from the CG force-field reconstruction by thresholding the basis function coefficients from each frequency band independently. We discuss the implementation of our wavelet-based MSCG approach and demonstrate its accuracy using two different condensed-phase systems, i.e. liquid water and methanol. Simulations of liquid argon have also been performed using a one-to-one mapping between atomistic and CG sites. The latter model allows to verify the accuracy of the method and to test different choices of wavelet families. Furthermore, the results of the computer simulations show that the efficiency and sparsity of the representation of the CG force field can be traced back to the mathematical properties of the chosen family of wavelets. This result is in agreement with what is known from the theory of multiresolution analysis of signals. © 2015.