Results 11 to 20 of about 1,148,156 (325)

Restricted orthogonal gradient projection for continual learning

open access: yesAI Open, 2023
Continual learning aims to avoid catastrophic forgetting and effectively leverage learned experiences to master new knowledge. Existing gradient projection approaches impose hard constraints on the optimization space for new tasks to minimize ...
Zeyuan Yang   +4 more
doaj   +2 more sources

Adaptive Orthogonal Projection for Batch and Online Continual Learning

open access: yesAAAI Conference on Artificial Intelligence, 2022
Catastrophic forgetting is a key obstacle to continual learning. One of the state-of-the-art approaches is orthogonal projection. The idea of this approach is to learn each task by updating the network parameters or weights only in the direction ...
Yiduo Guo   +3 more
semanticscholar   +2 more sources

An enhanced text classification model by the inverted attention orthogonal projection module

open access: yesConnection Science, 2023
The orthogonal projection method has made significant progress in text classification, especially in generating discriminative features. This method obtains more pure and suitable for classification features by projecting text features onto the ...
Hong Zhao, Chenpeng Zhang, Aolong Wang
doaj   +2 more sources

Multiple viewpoints projection hologram from multiple angular orthogonal projection images based on GPU

open access: yesShenzhen Daxue xuebao. Ligong ban
To solve the problem of slow generation of multiple viewpoint projection hologram, a novel method for synthesizing Fresnel holograms based on graphics processing unit (GPU) is proposed with multiple angular orthogonal projection images. Firstly, multiple
CAO Xuemei   +6 more
doaj   +2 more sources

Point Orthogonal Projection onto a Spatial Algebraic Curve

open access: yesMathematics, 2020
Point orthogonal projection onto a spatial algebraic curve plays an important role in computer graphics, computer-aided geometric design, etc. We propose an algorithm for point orthogonal projection onto a spatial algebraic curve based on Newton’s ...
Taixia Cheng   +3 more
doaj   +2 more sources

Multi-view 3D human pose estimation based on multi-scale feature by orthogonal projection [PDF]

open access: yesE3S Web of Conferences
Aiming at the problems of inaccurate estimation results, complicated matching of feature information in different views and poor robustness of the network model in complex scenes, a multi-view multi-person 3D human pose estimation model with multi-scale ...
Wang Yinghan   +3 more
doaj   +3 more sources

On the Orthogonal Projection of a Belief Function [PDF]

open access: yes, 2007
In this paper we study a new probability associated with any given belief function b, i.e. the orthogonal projection π[b] of b onto the probability simplex P. We provide an interpretation of π[b] in terms of a redistribution process in which the mass of each focal element is equally distributed among its subsets, establishing an interesting analogy ...
Cuzzolin, Fabio, Fabio Cuzzolin
openaire   +3 more sources

COMPUTER GRAPHICAL REPRESENTATION, IN TREBLE ORTHOGONAL PROJECTION, OF A POINT

open access: yesJournal of Industrial Design and Engineering Graphics, 2017
In the stages of understanding and study, by students, of descriptive geometry, the treble orthogonal projection of a point, creates problems in the situations in that one or more descriptive coordinates are zero.
Andrei Slonovschi, Liviu Pruna
doaj   +5 more sources

Dual-Domain Calibration Transfer Using Orthogonal Projection

open access: yesApplied Spectroscopy, 2018
We report the use of dual-domain regression models, which were built utilizing a wavelet prism decomposition and paired with transfer by orthogonal projection, for the calibration transfer of near-infrared (NIR) spectra.
Dominic Poerio, Steven D. Brown
semanticscholar   +2 more sources

Fusion and Orthogonal Projection for Improved Face-Voice Association [PDF]

open access: yesIEEE International Conference on Acoustics, Speech, and Signal Processing, 2021
We study the problem of learning association between face and voice. Prior works adopt pairwise or triplet loss formulations to learn an embedding space amenable for associated matching and verification tasks.
Muhammad Saeed   +4 more
semanticscholar   +1 more source

Home - About - Disclaimer - Privacy