English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Efficient and accurate polarimetric synthetic aperture radar (PolSAR) imageclassification with a limited number of prior labels is always full ofchallenges. For general supervised deep learning classification algorithms, thepixel-by-pixel algorithm achieves precise yet inefficient classification with asmall number of labeled pixels, whereas the pixel mapping algorithm achievesefficient yet edge-rough classification with more prior labels required. Totake efficiency, accuracy and prior labels into account, we propose a novelpixel-refining parallel mapping network in the complex domain named CRPM-Netand the corresponding training algorithm for PolSAR image classification.CRPM-Net consists of two parallel sub-networks: a) A transfer dilatedconvolution mapping network in the complex domain (C-Dilated CNN) activated bya complex cross-convolution neural network (Cs-CNN), which is aiming at preciselocalization, high efficiency and the full use of phase information; b) Acomplex domain encoder-decoder network connected parallelly with C-Dilated CNN,which is to extract more contextual semantic features. Finally, we design atwo-step algorithm to train the Cs-CNN and CRPM-Net with a small number oflabeled pixels for higher accuracy by refining misclassified labeled pixels. Weverify the proposed method on AIRSAR and E-SAR datasets. The experimentalresults demonstrate that CRPM-Net achieves the best classification results andsubstantially outperforms some latest state-of-the-art approaches in bothefficiency and accuracy for PolSAR image classification. The source code andtrained models for CRPM-Net is available at:https://github.com/PROoshio/CRPM-Net.

PolSAR Image Classification Based on Dilated Convolution and Pixel-Refining Parallel Mapping network in the Complex Domain