Results 1 to 10 of about 1,142,197 (195)
Orthogonal Projection Loss [PDF]
2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021 Deep neural networks have achieved remarkable performance on a range of classification tasks, with softmax cross-entropy (CE) loss emerging as the de-facto objective function. The CE loss encourages features of a class to have a higher projection score on the true class-vector compared to the negative classes. However, this is a relative constraint and
Kanchana Ranasinghe +4 more
openaire +4 more sources
Breast Cancer Detection with Low-dimension Ordered Orthogonal Projection in Terahertz Imaging. [PDF]
IEEE Trans Terahertz Sci Technol, 2020 This article proposes a new dimension reduction algorithm based on low-dimensional ordered orthogonal projection, which is used for cancer detection with terahertz (THz) images of freshly excised human breast cancer tissues.
Chavez T +4 more
europepmc +2 more sources
Application of Orthogonal Polynomial in Orthogonal Projection of Algebraic Surface
Axioms, 2022 Point orthogonal projection onto an algebraic surface is a very important topic in computer-aided geometric design and other fields. However, implementing this method is currently extremely challenging and difficult because it is difficult to achieve to ...
Xudong Wang, Xiaowu Li, Yuxia Lyu
doaj +2 more sources
Orthogonal Subspace Projection Target Detector for Hyperspectral Anomaly Detection
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021 Orthogonal subspace projection (OSP) is a versatile hyperspectral imaging technique which has shown great potential in dimensionality reduction, target detection, spectral unmixing, etc. However, due to its inherent requirement of prior target knowledge,
Chein-I Chang, Hongju Cao, Meiping Song
doaj +2 more sources
SOP: Selective Orthogonal Projection for Composed Image Retrieval [PDF]
SensorsThe proliferation of intelligent sensor networks in urban surveillance and remote sensing has triggered the explosive growth of unstructured visual sensor data.
Su Cheng, Guoyang Liu
doaj +2 more sources
On the perturbation of an $L^2$-orthogonal projection
J. Comput. Appl. Math., 2018 The $L^2$-orthogonal projection onto a subspace is an important mathematical tool, which has been widely applied in many fields such as linear least squares problems, eigenvalue problems, ill-posed problems, and randomized algorithms. In some numerical applications, the entries of a matrix will seldom be known exactly, so it is necessary to develop ...
Xuefeng Xu
openaire +4 more sources
Orthogonal projection of points in CAD/CAM applications: an overview
Journal of Computational Design and Engineering, 2014 This paper aims to review methods for computing orthogonal projection of points onto curves and surfaces, which are given in implicit or parametric form or as point clouds. Special emphasis is place on orthogonal projection onto conics along with reviews
Kwang Hee Ko +2 more
exaly +2 more sources
An Orthogonal Projection Algorithm to Suppress Interference in High-Frequency Surface Wave Radar
Remote Sensing, 2018 High-frequency surface wave radar (HFSWR) has been widely applied in sea-state monitoring, and its performance is known to suffer from various unwanted interferences and clutters.
Zezong Chen, Fei Xie, Chen Zhao
exaly +2 more sources
GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients [PDF]
Neural Information Processing Systems, 2023 Detecting out-of-distribution (OOD) data is crucial for ensuring the safe deployment of machine learning models in real-world applications. However, existing OOD detection approaches primarily rely on the feature maps or the full gradient space ...
Sima Behpour +5 more
semanticscholar +1 more source
Randomized Orthogonal Projection Methods for Krylov Subspace Solvers [PDF]
arXiv.org, 2023 Randomized orthogonal projection methods (ROPMs) can be used to speed up the computation of Krylov subspace methods in various contexts. Through a theoretical and numerical investigation, we establish that these methods produce quasi-optimal ...
E. Timsit, L. Grigori, O. Balabanov
semanticscholar +1 more source