Results 1 to 10 of about 1,005,453 (288)

Few-Shot Learning for Plant-Disease Recognition in the Frequency Domain

open access: yesPlants, 2022
Few-shot learning (FSL) is suitable for plant-disease recognition due to the shortage of data. However, the limitations of feature representation and the demanding generalization requirements are still pressing issues that need to be addressed.
Hong Lin   +4 more
doaj   +4 more sources

Learning in the Frequency Domain [PDF]

open access: yes2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020
Deep neural networks have achieved remarkable success in computer vision tasks. Existing neural networks mainly operate in the spatial domain with fixed input sizes.
Kai Xu   +5 more
semanticscholar   +4 more sources

Frequency-domain Learning for Volumetric-based 3D Data Perception [PDF]

open access: yesarXiv.org, 2023
Frequency-domain learning draws attention due to its superior tradeoff between inference accuracy and input data size. Frequency-domain learning in 2D computer vision tasks has shown that 2D convolutional neural networks (CNN) have a stationary spectral ...
Zifan Yu, Suya You, Fengbo Ren
semanticscholar   +3 more sources

Leveraging Frequency Domain Learning in 3D Vessel Segmentation

open access: yes2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2023
Coronary microvascular disease constitutes a substantial risk to human health. Employing computer-aided analysis and diagnostic systems, medical professionals can intervene early in disease progression, with 3D vessel segmentation serving as a crucial ...
Xinyuan Wang   +6 more
semanticscholar   +3 more sources

Transform Once: Efficient Operator Learning in Frequency Domain [PDF]

open access: yesAdvances in Neural Information Processing Systems 35, 2022
Spectral analysis provides one of the most effective paradigms for information-preserving dimensionality reduction, as simple descriptions of naturally occurring signals are often obtained via few terms of periodic basis functions. In this work, we study
Michael Poli   +6 more
semanticscholar   +4 more sources

Learning Frequency Domain Priors for Image Demoireing [PDF]

open access: yesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
Image demoireing is a multi-faceted image restoration task involving both moire pattern removal and color restoration. In this paper, we raise a general degradation model to describe an image contaminated by moire patterns, and propose a novel multi ...
Bolun Zheng   +8 more
semanticscholar   +4 more sources

P-Wave detection using deep learning in time and frequency domain for imbalanced dataset

open access: yesHeliyon, 2021
Early tsunami and earthquake warning systems need a good Automatic First Arrival Picking (AFAP) subsystem to determine the earthquake arrival time.
Rhesa Aditya Sugondo, Carmadi Machbub
doaj   +3 more sources

Continual Learning in the Frequency Domain

open access: yesAdvances in Neural Information Processing Systems 37
Continual learning (CL) is designed to learn new tasks while preserving existing knowledge. Replaying samples from earlier tasks has proven to be an effective method to mitigate the forgetting of previously acquired knowledge.
Ruiqi Liu   +5 more
semanticscholar   +4 more sources

Spatial-frequency complementary fusion network for dehazing with multi-scale and attention modules [PDF]

open access: yesScientific Reports
Single image dehazing is a challenging ill-posed problem. It aims to estimate the latent haze-free image from the observed hazy image. In recent years, learning-based methods have demonstrated their superiority in single image dehazing.
Chenguang Yan, Gang Liu
doaj   +2 more sources

Hyperspectral Anomaly Detection Using Dual-Branch Network Based on Frequency Domain Learning

open access: yesIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Existing deep learning-based hyperspectral anomaly detection methods often overlook frequency domain features, hindering the ability to effectively distinguish between background and anomalies.
Xiaoyi Wang   +6 more
doaj   +2 more sources

Home - About - Disclaimer - Privacy