Aeromagnetic Compensation Algorithm Based on Levenberg-Marquard Neural Network [PDF]
Journal of Geodesy and Geoinformation Science, 2021 The magnetic compensation of aeromagnetic survey is an important calibration work, which has a great impact on the accuracy of measurement. In an aeromagnetic survey flight, measurement data consists of diurnal variation, aircraft maneuver interference ...
Li LIU,Qingfeng XU,Hui GU,Lei ZHOU,Zhenfu LIU,Lili CAO
doaj +1 more source
FreeNeRF: Improving Few-Shot Neural Rendering with Free Frequency Regularization [PDF]
Computer Vision and Pattern Recognition, 2023 Novel view synthesis with sparse inputs is a challenging problem for neural radiance fields (NeRF). Recent efforts alleviate this challenge by introducing external supervision, such as pre-trained models and extra depth signals, or by using non-trivial ...
Jiawei Yang, M. Pavone, Yue Wang
semanticscholar +1 more source
Elastic Net Regularization Paths for All Generalized Linear Models [PDF]
Journal of Statistical Software, 2021 The lasso and elastic net are popular regularized regression models for supervised learning. Friedman, Hastie, and Tibshirani (2010) introduced a computationally efficient algorithm for computing the elastic net regularization path for ordinary least ...
J. K. Tay, B. Narasimhan, T. Hastie
semanticscholar +1 more source
Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks [PDF]
ACM Computing Surveys, 2022 Several image processing tasks, such as image classification and object detection, have been significantly improved using Convolutional Neural Networks (CNN).
C. F. G. Santos, J. Papa
semanticscholar +1 more source
A Hybrid Regularization Operator and Its Application in Seismic Inversion
IEEE Access, 2021 Seismic inversion is an effective tool to estimate the properties of subsurface strata from seismograms. However, the intrinsic ill-posedness of the inversion problem causes the inverted subsurface properties to be easily polluted by inversion errors due
Yangting Liu +3 more
doaj +1 more source
A four directions variational method for solving image processing problems [PDF]
Iranian Journal of Numerical Analysis and Optimization, 2020 In this paper, based on a discrete total variation model, a modified discretization of total variation (TV) is introduced for image processing problems.
Alireza H., E.E. Esfahani
doaj +1 more source
SelfReg: Self-supervised Contrastive Regularization for Domain Generalization [PDF]
IEEE International Conference on Computer Vision, 2021 In general, an experimental environment for deep learning assumes that the training and the test dataset are sampled from the same distribution. However, in real-world situations, a difference in the distribution between two datasets, i.e.
Daehee Kim +3 more
semanticscholar +1 more source
CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features [PDF]
IEEE International Conference on Computer Vision, 2019 Regional dropout strategies have been proposed to enhance performance of convolutional neural network classifiers. They have proved to be effective for guiding the model to attend on less discriminative parts of objects (e.g.
Sangdoo Yun +5 more
semanticscholar +1 more source
Combating Noisy Labels by Agreement: A Joint Training Method with Co-Regularization [PDF]
Computer Vision and Pattern Recognition, 2020 Deep Learning with noisy labels is a practically challenging problem in weakly-supervised learning. The state-of-the-art approaches "Decoupling" and "Co-teaching+" claim that the "disagreement" strategy is crucial for alleviating the problem of learning ...
Hongxin Wei +3 more
semanticscholar +1 more source
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017 We propose a new regularization method based on virtual adversarial loss: a new measure of local smoothness of the conditional label distribution given input.
Takeru Miyato +3 more
semanticscholar +1 more source