Bibliographies thématiques / Steerable Convolutions

Sommaire

Articles de revues
Thèses
Actes de conférences

Littérature scientifique sur le sujet « Steerable Convolutions »

Auteur : Grafiati

Publié le 25 janvier 2025

Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres

Choisissez une source :

Consultez les listes thématiques d’articles de revues, de livres, de thèses, de rapports de conférences et d’autres sources académiques sur le sujet « Steerable Convolutions ».

À côté de chaque source dans la liste de références il y a un bouton « Ajouter à la bibliographie ». Cliquez sur ce bouton, et nous générerons automatiquement la référence bibliographique pour la source choisie selon votre style de citation préféré : APA, MLA, Harvard, Vancouver, Chicago, etc.

Vous pouvez aussi télécharger le texte intégral de la publication scolaire au format pdf et consulter son résumé en ligne lorsque ces informations sont inclues dans les métadonnées.

Articles de revues sur le sujet "Steerable Convolutions"

Diaz, Ivan, Mario Geiger et Richard Iain McKinley. « Leveraging SO(3)-steerable convolutions for pose-robust semantic segmentation in 3D medical data ». Machine Learning for Biomedical Imaging 2, May 2024 (15 mai 2024) : 834–55. http://dx.doi.org/10.59275/j.melba.2024-7189.

Texte intégral

Résumé :

Convolutional neural networks (CNNs) allow for parameter sharing and translational equivariance by using convolutional kernels in their linear layers. By restricting these kernels to be SO(3)-steerable, CNNs can further improve parameter sharing and equivariance. These equivariant convolutional layers have several advantages over standard convolutional layers, including increased robustness to unseen poses, smaller network size, and improved sample efficiency. Despite this, most segmentation networks used in medical image analysis continue to rely on standard convolutional kernels. In this paper, we present a new family of segmentation networks that use equivariant voxel convolutions based on spherical harmonics. These SE(3)-equivariant volumetric segmentation networks, which are robust to data poses not seen during training, do not require rotation-based data augmentation during training. In addition, we demonstrate improved segmentation performance in MRI brain tumor and healthy brain structure segmentation tasks, with enhanced robustness to reduced amounts of training data and improved parameter efficiency. Code to reproduce our results, and to implement the equivariant segmentation networks for other tasks is available at <a href='http://github.com/SCAN-NRAD/e3nn_Unet'>http://github.com/SCAN-NRAD/e3nn_Unet</a>.

Styles APA, Harvard, Vancouver, ISO, etc.

Marshall, Nicholas F., Oscar Mickelin et Amit Singer. « Fast Expansion into Harmonics on the Disk : A Steerable Basis with Fast Radial Convolutions ». SIAM Journal on Scientific Computing 45, n^o 5 (22 septembre 2023) : A2431—A2457. http://dx.doi.org/10.1137/22m1542775.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Zhu, B., J. Zhang, T. Tang et Y. Ye. « SFOC : A NOVEL MULTI-DIRECTIONAL AND MULTI-SCALE STRUCTURAL DESCRIPTOR FOR MULTIMODAL REMOTE SENSING IMAGE MATCHING ». International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLIII-B2-2022 (30 mai 2022) : 113–20. http://dx.doi.org/10.5194/isprs-archives-xliii-b2-2022-113-2022.

Texte intégral

Résumé :

Abstract. Accurate matching of multimodal remote sensing (RS) images (e.g., optical, infrared, LiDAR, SAR, and rasterized maps) is still an ongoing challenge because of nonlinear radiometric differences (NRD) between these images. Considering that structural properties are preserved between multimodal images, this paper proposes a robust matching method based on multi-directional and multi-scale structural features, which consist of two critical steps. Firstly, a novel structural descriptor named the Steerable Filters of first- and second-Order Channels (SFOC) is constructed to address severe NRD, which combines the first- and second-order gradient information by using the steerable filters to depict multi-directional and multi-scale structural features of images. Meanwhile, SFOC is further enhanced by performing the dilated Gaussian convolutions with different dilated rates on it, which can capture multi-level context structural features and improve the ability to resist noise. Then, a fast similarity measure, called Fast Normalized Cross-Correlation (Fast-NCCSFOC), is established to detect correspondences by a template matching scheme, which employs the Fast Fourier Transform (FFT) technique and the integral image to improve the matching efficiency. The performance of the proposed SFOC has been evaluated with many different kinds of multimodal RS images, and experimental results show its superior matching performance compared with the state-of-the-art methods.

Styles APA, Harvard, Vancouver, ISO, etc.

Zhong, Jiaxin, Haishan Zou, Jing Lu et Dong Zhang. « A modified convolution model for calculating the far field directivity of a parametric array loudspeaker ». Journal of the Acoustical Society of America 153, n^o 3 (mars 2023) : 1439–51. http://dx.doi.org/10.1121/10.0017361.

Texte intégral

Résumé :

The far field directivity is a straightforward indicator to describe the radiation pattern of the audio sound generated by a parametric array loudspeaker (pal), but its accurate and computationally efficient prediction is still challenging at present. This paper derives two-dimensional (2D), three-dimensional (3D), and 3D axisymmetric convolution models for calculating the far field directivity based on the quasilinear solution of Westervelt equation. The obtained expressions are expressed as linear and spherical convolutions of the ultrasound directivity and Westervelt directivity for 2D and 3D models, respectively. To improve prediction accuracy, the obtained expression is multiplied by an effective directivity resulted from the aperture factor of audio sound. The calculated directivities are compared against the exact solution obtained using the cylindrical and spherical wave expansions for 2D and 3D models, respectively. Numerical results with piston, apodized, and steerable profiles in both 2D and 3D models show that the proposed modified convolution model agrees well with the exact solution. It is also found that sidelobes appear in the audio sound directivity at large aperture sizes and high audio frequencies due to the aperture factor of audio sound, which can be predicted with the proposed method with a relatively low computational expenditure.

Styles APA, Harvard, Vancouver, ISO, etc.

Hitzer, Eckhard. « General Steerable Two-sided Clifford Fourier Transform, Convolution and Mustard Convolution ». Advances in Applied Clifford Algebras 27, n^o 3 (9 juin 2016) : 2215–34. http://dx.doi.org/10.1007/s00006-016-0687-5.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Hitzer, Eckhard. « Quaternionic Wiener–Khinchine Theorems and Spectral Representation of Convolution with Steerable Two-sided Quaternion Fourier Transform ». Advances in Applied Clifford Algebras 27, n^o 2 (2 décembre 2016) : 1313–28. http://dx.doi.org/10.1007/s00006-016-0744-0.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Jin, Yuzhen, Jiehao Chen et Jingyu Cui. « Fast flow field prediction based on E(2)-equivariant steerable convolutional neural networks ». Physics of Fluids 36, n^o 9 (1 septembre 2024). http://dx.doi.org/10.1063/5.0219221.

Texte intégral

Résumé :

In the field of flow field reconstruction, traditional deep learning models predominantly rely on standard convolutions, but their predictive accuracy remains limited. To address this issue, we explore the potential of E(2)-equivariant convolutions to enhance the predictive accuracy of deep learning models for fast flow field prediction. Unlike conventional convolutions, E(2)-equivariant convolutions offer a richer representation capability by better capturing geometric and structural information. Our neural network integrates an attention mechanism that leverages the signed distance function (SDF) to encode geometric details and an indicator matrix to incorporate boundary conditions. The model predicts velocity and pressure fields as outputs. We conducted experiments specifically targeting non-uniform steady laminar flows, and the results show a 16.1% reduction in overall error compared to models based on traditional convolutions while maintaining high efficiency. These findings indicate that E(2)-equivariant convolution, coupled with an attention mechanism, significantly improves flow field prediction by focusing on critical information and better representing complex geometries.

Styles APA, Harvard, Vancouver, ISO, etc.

Vidacic, Dragan, et Richard A. Messner. « BIOLOGICALLY INSPIRED FILTERS UTILIZING SPECTRAL PROPERTIES OF TOEPLITZ-BLOCK-TOEPLITZ MATRICES ». International Journal of Computing, 28 décembre 2015, 198–207. http://dx.doi.org/10.47839/ijc.14.4.820.

Texte intégral

Résumé :

The construction of filters arising from linear neural networks with feed-backward excitatory-inhibitory connections is presented. Spatially invariant coupling between neurons and the distribution of neuron-receptor units in the form of a uniform square grid yield the TBT (Toeplitz-Block-Toeplitz) connection matrix. Utilizing the relationship between spectral properties of such matrices and their generating functions, the method for construction of recurrent linear networks is addressed. By appropriately bounding the generating function, the connection matrix eigenvalues are kept in the desired range allowing for large matrix inverse to be approximated by a convergent power series. Instead of matrix inversion, the single pass convolution with the filter obtained from the network connection weights is applied when solving the network. For the case of inter-neuron coupling in the form of a function that is expandable in a Fourier series in polar angle, the network response filter is shown to be steerable.

Styles APA, Harvard, Vancouver, ISO, etc.

Thèses sur le sujet "Steerable Convolutions"

Joginipelly, Arjun. « Implementation of Separable & ; Steerable Gaussian Smoothers on an FPGA ». ScholarWorks@UNO, 2010. http://scholarworks.uno.edu/td/98.

Texte intégral

Résumé :

Smoothing filters have been extensively used for noise removal and image restoration. Directional filters are widely used in computer vision and image processing tasks such as motion analysis, edge detection, line parameter estimation and texture analysis. It is practically impossible to tune the filters to all possible positions and orientations in real time due to huge computation requirement. The efficient way is to design a few basis filters, and express the output of a directional filter as a weighted sum of the basis filter outputs. Directional filters having these properties are called "Steerable Filters." This thesis work emphasis is on the implementation of proposed computationally efficient separable and steerable Gaussian smoothers on a Xilinx VirtexII Pro FPGA platform. FPGAs are Field Programmable Gate Arrays which consist of a collection of logic blocks including lookup tables, flip flops and some amount of Random Access Memory. All blocks are wired together using an array of interconnects. The proposed technique [2] is implemented on a FPGA hardware taking the advantage of parallelism and pipelining.

Styles APA, Harvard, Vancouver, ISO, etc.

Pezzicoli, Francesco. « Statistical Physics - Machine Learning Interplay : from Addressing Class Imbalance with Replica Theory to Predicting Dynamical Heterogeneities with SE(3)-equivariant Graph Neural Networks ». Electronic Thesis or Diss., université Paris-Saclay, 2024. http://www.theses.fr/2024UPASG115.

Texte intégral

Résumé :

Cette thèse explore la relation entre l'Apprentissage Automatique (AA) et la Physique Statistique (PS), en abordant deux défis importants à l'interface entre ces deux domaines. Tout d'abord, j'examine le problème du Déséquilibre de Classe (DC) dans le cadre de l'apprentissage supervisé en introduisant un modèle analytiquement solvable basé sur la mécanique statistique: je propose un cadre théorique pour analyser et interpréter le problème de DC. Certains phénomènes non triviaux sont observés : par exemple, un ensemble d'entraînement équilibré aboutit souvent à une performance sous-optimale. Ensuite, j'étudie le phénomène de blocage dynamique dans les verres structuraux à l'aide de modèles avancés d'AA. En exploitant des réseaux de neurones sur graphe qui sont SE(3)-équivariants, j'atteins des performance qui atteignent ou surpassent l'état de l'art pour la prédiction des propriétés dynamiques à partir de la structure statique. Cela suggère l'émergence d'un "ordre amorphe" qui est corrélé avec la dynamique. Cela souligne également l'importance des features directionnelles dans l'identification de cet ordre. Ensemble, ces contributions démontrent le potentiel de la physique statistique pour résoudre les défis de l'AA et l'utilité des modèles d'AA pour faire progresser les sciences physiques
This thesis explores the relationship between Machine Learning (ML) and Statistical Physics (SP), addressing two significant challenges at the interface between the two fields. First, I examine the problem of Class Imbalance (CI) in the supervised learning set-up by introducing an analytically tractable model grounded in statistical mechanics: I provide a theoretical framework to analyze and interpret CI. Some non-trivial phenomena are observed: for example, a balanced training set often results in sub-optimal performance. Second, I study the phenomenon of dynamical arrest in supercooled liquids through advanced ML models. Leveraging SE(3)-equivariant Graph Neural Networks, I am able to reach or surpass state-of-the art accuracy in the task of prediction of dynamical properties from static structure. This suggests the emergence of a growing "amorphous order" that correlates with particle dynamics. It also emphasizes the importance of directional features in identifying this order. Together, these contributions demonstrate the potential of SP in addressing ML challenges and the utility of ML models in advancing physical sciences

Styles APA, Harvard, Vancouver, ISO, etc.

Actes de conférences sur le sujet "Steerable Convolutions"

Vasukidevi, G., Gulshan Dhasmana, Madhavi Kappagantula, Shalini S, Harshal Patil et Ramya Maranan. « Automatic Scene Text Extraction and Recognition Using Steerable Convolutional Neural Network with Fennec Fox Optimization ». Dans 2024 Second International Conference on Intelligent Cyber Physical Systems and Internet of Things (ICoICI), 1602–8. IEEE, 2024. http://dx.doi.org/10.1109/icoici62503.2024.10696175.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Alves Pereira, Luis F., Jan De Beenhouwer et Jan Sijbers. « The Deep Steerable Convolutional Framelet Network for Suppressing Directional Artifacts in X-ray Tomosynthesis ». Dans 2023 31st European Signal Processing Conference (EUSIPCO). IEEE, 2023. http://dx.doi.org/10.23919/eusipco58844.2023.10289781.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Janjic, Jovana, Awaz Ali, Frits Mastik, Merel D. Leistikow, Johan G. Bosch, Paul Breedveld, Antonius F. W. Van der Steen et Gijs Van Soest. « Volumetric ultrasound image reconstruction from a single-element forward-looking intracardiac steerable catheter using 3D adaptive normalized convolution ». Dans 2018 IEEE International Ultrasonics Symposium (IUS). IEEE, 2018. http://dx.doi.org/10.1109/ultsym.2018.8580024.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

Roshanfar, Majid, Pedram Fekri et Javad Dargahi. « A Deep Learning Model for Tip Force Estimation on Steerable Catheters Via Learning-From-Simulation ». Dans THE HAMLYN SYMPOSIUM ON MEDICAL ROBOTICS. The Hamlyn Centre, Imperial College London London, UK, 2023. http://dx.doi.org/10.31256/hsmr2023.17.

Texte intégral

Résumé :

Atrial Fibrillation (AFib) is the most common arrhyth- mia among the elderly population, where electrical activity becomes chaotic, leading to blood clots and strokes. During Radio Frequency Ablation (RFA), the arrhythmogenic sites within the cardiac tissue are burned off to reduce the undesired pulsation. Manual catheters are used for most atrial ablations, however, robotic catheter intervention systems provide more precise map- ping. Several studies showed excessive contact forces (> 0.45 N) increase the incidence of tissue perforation, while inadequate force (< 0.1 N) results in ineffective ablation. Fig.1 shows a schematic of a cardiac RFA catheter used for AFib treatment. For robot-assisted RFA to be safe and effective, real-time force estimation of catheter’s tip is required. As a solution, finite element (FE) analysis can provide a useful tool to estimate the real-time tip contact force. In this work, a nonlinear planar FE model of a steerable catheter was first developed with parametric material properties in ANSYS software. After that, a series of simulations based on each mechanical property was performed, and the deformed shape of the catheter was recorded. Next, validation was conducted by comparing the results of the simulation with experimental results between the range of 0-0.45 N to determine the material properties. Despite the previous work, which was a study to estimate the tip contact force of a catheter using a deep convolutional neural network [1], [2], the main contribution of this study was proposing a synthetic data generation, so as to train a light deep learning (DL) architecture for tip force estimation according to the FE simulations. Due to the availability of real-time X-ray images during RFA procedures (fluoroscopy), the shape of the catheter is available intraoperatively. The proposed solution not only feeds the data-hungry methods based on DL with a sufficient amount of data, but also shows the feasibility of replacing the fast, accurate, and light-weight learning-based methods with slow simulations.

Styles APA, Harvard, Vancouver, ISO, etc.

Nous offrons des réductions sur tous les plans premium pour les auteurs dont les œuvres sont incluses dans des sélections littéraires thématiques. Contactez-nous pour obtenir un code promo unique!