Results 31 to 40 of about 10,742,237 (292)

FDMamba: frequency-enhanced deformable Mamba for topology-aware road extraction

GIScience & Remote Sensing
Extracting topological road networks from high-resolution remote sensing imagery is a fundamental yet challenging task, often hindered by slender geometries and complex occlusions.
Zhengbo Yu, Binbin Li, Dongsheng Zhong, Zhe Chen, Weirong Yang, Zhongchang Sun, Keyan Xiao, Cheng Li, Lorenzo Picco   +8 more
doaj   +1 more source

A High-Resolution Remote Sensing Road Extraction Method Based on the Coupling of Global Spatial Features and Fourier Domain Features

Remote Sensing
Remote sensing road extraction based on deep learning is an important method for road extraction. However, in complex remote sensing images, different road information often exhibits varying frequency distributions and texture characteristics, and it is ...
Hui Yang, Caili Zhou, Xiaoyu Xing, Yongchuang Wu, Yanlan Wu   +4 more
doaj   +1 more source

Continual Learning in the Frequency Domain

Advances 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. However, the current research on the training efficiency of rehearsal-based methods is insufficient, which limits the practical
Ruiqi Liu, Boyu Diao, Libo Huang, Zijia An, Zhulin An, Yongjun Xu 0001   +5 more
openaire   +4 more sources

Learned Lossless Compression for JPEG via Frequency-Domain Prediction

CoRR, 2023
JPEG images can be further compressed to enhance the storage and transmission of large-scale image datasets. Existing learned lossless compressors for RGB images cannot be well transferred to JPEG images due to the distinguishing distribution of DCT coefficients and raw pixels.
Jixiang Luo, Shaohui Li, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong   +5 more
openaire   +2 more sources

Efficient Aero-Optical Degraded Image Restoration via Adaptive Frequency Selection

Remote Sensing
During high-speed flight, the aircraft causes rapid compression of the surrounding air, creating a complex turbulent flow field. This high-speed flow field interferes with the optical transmission of optical imaging systems, resulting in high-frequency ...
Yingjiao Huang, Qingpeng Zhang, Xiafei Ma, Haotong Ma   +3 more
doaj   +1 more source

A Frequency-Domain Convolutional Neural Network Architecture Based on the Frequency-Domain Randomized Offset Rectified Linear Unit and Frequency-Domain Chunk Max Pooling Method

IEEE Access, 2020
It is of great importance to construct a convolutional neural network architecture in the frequency domain to explore the theory of deep learning in the frequency domain.
Jinhua Lin, Lin Ma, Jingxia Cui
doaj   +1 more source

Multiplexing a serial array of tapered optical fibre sensors using coherent optical frequency domain reflectometry [PDF]

, 2012
The use of high spatial resolution optical frequency domain reflectometry (OFDR) to facilitate the multiplexing of a serial array of tapered optical fibre sensors is presented.
Tatam, Ralph P., Chehura, Edmon, James, Stephen W., Jarzebinska, Renata   +3 more
core   +1 more source

PWFNet: Pyramidal Wavelet–Frequency Attention Network for Road Extraction

Remote Sensing
Road extraction from remote sensing imagery plays a critical role in applications such as autonomous driving, urban planning, and infrastructure development. Although deep learning methods have achieved notable progress, current approaches still struggle
Jinkun Zong, Yonghua Sun, Ruozeng Wang, Dinglin Xu, Xue Yang, Xiaolin Zhao   +5 more
doaj   +1 more source

Spatial-Spectral Synergy Learning in the Frequency Domain for Hyperspectral Image Super-Resolution

IEEE Access
Hyperspectral image super-resolution using deep learning has achieved remarkable results. However, most of methods are developed in the spatial domain and rarely explore solutions in the frequency domain.
Yikai Duan, Jianwen Hu, Kaixiang Xie
doaj   +1 more source

Frequency-Domain Learning for Volumetric-Based 3d Data Perception

, 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 bias towards low-frequency channels so that high-frequency channels can be pruned with no or little ...
Zifan Yu, Suya You, Fengbo Ren
openaire   +3 more sources