Results 21 to 30 of about 48,655 (263)
Moment Matching Denoising Gibbs Sampling
Advances in Neural Information Processing Systems 36, 2023 Energy-Based Models (EBMs) offer a versatile framework for modeling complex data distributions. However, training and sampling from EBMs continue to pose significant challenges. The widely-used Denoising Score Matching (DSM) method for scalable EBM training suffers from inconsistency issues, causing the energy model to learn a `noisy' data distribution.
Mingtian Zhang +3 more
openaire +3 more sources
Remote Sensing, 2023 Optical and SAR image registration is the primary procedure to exploit the complementary information from the two different image modal types. Although extensive research has been conducted to narrow down the vast radiometric and geometric gaps so as to ...
Han Zhang +6 more
doaj +1 more source
Study on terrain radiant correction of high spatial resolution image of mountainous area
浙江大学学报. 农业与生命科学版, 2006 High spatial resolution remote sensing images such as satellite image and airborne image are much widely used in agriculture, forestry recourses inventory and the mountain ecology monitoring area.
ZHANG Chao +4 more
doaj +1 more source
One-loop matching of the CP-odd three-gluon operator to the gradient flow
Physics Letters B, 2023 The calculation of the neutron electric dipole moment within effective field theories for physics beyond the Standard Model requires non-perturbative hadronic matrix elements of effective operators composed of quark and gluon fields.
Òscar L. Crosas +4 more
doaj +1 more source
Generative Moment Matching Networks
CoRR, 2015 We consider the problem of learning deep generative models from data. We formulate a method that generates an independent sample via a single feedforward pass through a multilayer perceptron, as in the recently proposed generative adversarial networks (Goodfellow et al., 2014).
Yujia Li 0001 +2 more
openaire +3 more sources
Research on an Underwater Target-Tracking Method Based on Zernike Moment Feature Matching
Journal of Marine Science and Engineering, 2023 Sonar images have the characteristics of lower resolution and blurrier edges compared to optical images, which make the feature-matching method in underwater target tracking less robust.
Wenhan Gao +7 more
doaj +1 more source
Deep Transfer Learning Method Based on Automatic Domain Alignment and Moment Matching
Mathematics, 2022 Domain discrepancy is a key research problem in the field of deep domain adaptation. Two main strategies are used to reduce the discrepancy: the parametric method and the nonparametric method.
Jingui Zhang +4 more
doaj +1 more source
One-loop matching of CP-odd four-quark operators to the gradient-flow scheme
Journal of High Energy Physics, 2023 The translation of experimental limits on the neutron electric dipole moment into constraints on heavy CP-violating physics beyond the Standard Model requires knowledge about non-perturbative matrix elements of effective operators, which ideally should ...
Jona Bühler, Peter Stoffer
doaj +1 more source
Moment-Based Stochastic Analysis of a Bistable Energy Harvester with Matching Network
Applied Sciences, 2023 We discuss the analysis of a piezoelectric energy harvester for random mechanical vibrations, and we assess the performance improvement guaranteed by interposing a matching network between the transducer and the electrical load, in terms of average ...
Kailing Song +3 more
doaj +1 more source
Structured Model Order Reduction of System-Level Power Delivery Networks
IEEE AccessThis paper proposes a comprehensive model order reduction framework to enable fast power integrity verification at the system level. This approach is developed to compress models of complete power delivery networks of high-end multiprocessor systems ...
Antonio Carlucci +3 more
doaj +1 more source