[논문]Kick: Shift-N-Overlap Cascades of Transposed Convolutional Layer for Better Autoencoding Reconstruction on Remote Sensing Imagery

Hong, Seungkyun; Song, Sa-Kwang

doi:10.1109/access.2020.3000557

[해외논문] Kick: Shift-N-Overlap Cascades of Transposed Convolutional Layer for Better Autoencoding Reconstruction on Remote Sensing Imagery 원문보기

IEEE access : practical research, open solutions, v.8, 2020년, pp.107244 - 107259

Hong, Seungkyun (Department of Data and HPC Science, Korea University of Science and Technology (UST), Daejeon, South Korea) , Song, Sa-Kwang (Department of Data and HPC Science, Korea University of Science and Technology (UST), Daejeon, South Korea)

Abstract ▼ AI-Helper

A convolutional autoencoder is an essential deep neural model architecture for understanding and predicting large-scale and widespread multi-dimensional information such as remote sensing imagery. To training a convolutional autoencoder, an automatic image reconstruction from input data and evaluation is repeatedly performed to achieve optimal reconstruction performance. Checkerboard artifacts, which are frequently produced on output images and lead to degraded image quality, are a significant issue during image reconstruction using a convolutional autoencoder. To remedy this coarse visual saliency issue during model training, we propose the ‘Kick’ deconvolutional layer - a cascaded transposed convolutional layer with pixel shifting and overlapping for checkerboard pattern smoothing. By using pixel-shifted identity convolutional layers, we improved image reconstruction performance using fewer trainable decoder parameters than previously suggested models without losing reconstruction capability. Moreover, our proposed layer can be used with any type of convolutional autoencoder, including typical convolutional autoencoders and adversarial autoencoders. To evaluate an image reconstruction performance of our suggested deconvolutional layer, we used a dataset containing 12 years of geostationary satellite observation data of East Asia.

참고문헌 (33)

2019
2019
Wang, Zhou, Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing : a publication of the IEEE Signal Processing Society, vol.13, no.4, 600-612.

상세보기
arXiv 1412 6980 Adam: A method for stochastic optimization kingma 2014
10.1109/CVPR.2010.5539957
10.1109/ICCV.2011.6126474
Proc Selected Papers Oxford Int Workshop Field Program Logic Appl More FPGAs Parameterized convolution filtering in an FPGA shoup 0 274
Hinton, G.E.. A Practical Guide to Training Restricted Boltzmann Machines. Lecture notes in computer science, vol.7700, 599-620.

상세보기
10.1145/2820903.2820918
10.1109/IGARSS.2016.7729856
10.1109/CVPR.2015.7298594
10.1109/CVPR.2016.90
Inception-v4 inception-resnet and the impact of residual connections on learning szegedy 2017
10.23915/distill.00003
Proc 13th Int Conf Artif Intell Statist Understanding the difficulty of training deep feedforward neural networks glorot 2010 249
Hinton, G. E., Salakhutdinov, R. R.. Reducing the Dimensionality of Data with Neural Networks. Science, vol.313, no.5786, 504-507.

상세보기
arXiv 1511 05644 Adversarial autoencoders makhzani 2015
Brown, Andrew, Milton, Sean, Cullen, Mike, Golding, Brian, Mitchell, John, Shelly, Ann. Unified Modeling and Prediction of Weather and Climate: A 25-Year Journey. Bulletin of the American Meteorological Society, vol.93, no.12, 1865-1877.

상세보기
Proc Adv Neural Inf Process Syst Extremeweather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events racah 2017 3402
arXiv 1609 04747 An overview of gradient descent optimization algorithms ruder 2016
Masci, J., Meier, U., Ciresan, D., Schmidhuber, J.. Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction. Lecture notes in computer science, vol.6791, 52-59.

상세보기
10.1109/CVPR.2015.7299155
10.1109/SC.2018.00054
10.1175/1525-7541(2003)004<1168:DQPFUI>2.0.CO;2

상세보기
arXiv 1606 07757 A taxonomy and library for visualizing learned features in convolutional neural networks grün 2016
Golding, B.W. Quantitative precipitation forecasting in the UK. Journal of hydrology, vol.239, no.1, 286-305.

상세보기
IEEE Trans Pattern Anal Mach Intell Pixel transposed convolutional networks gao 2020 42 1218

상세보기
10.1117/12.974495
Proc EUMETSAT Meteorol Satell Conf Darmstadt Status of Japanese Meteorological Satellites and recent activities of MSC uesawa 2006 12
10.1109/ISPASS.2017.7975270
Observing systems capability analysis and review tool (OSCAR) 2019
Proc M Usenix Gnu parallel—The command-line power tool tange 2011 36 42
10.1109/CANDAR.2017.27

LOADING...

활용도 분석정보

상세보기

다운로드

내보내기

활용도 Top5 논문

해당 논문의 주제분야에서 활용도가 높은 상위 5개 콘텐츠를 보여줍니다.
더보기 버튼을 클릭하시면 더 많은 관련자료를 살펴볼 수 있습니다.

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증

[해외논문] Kick: Shift-N-Overlap Cascades of Transposed Convolutional Layer for Better Autoencoding Reconstruction on Remote Sensing Imagery 원문보기

Abstract ▼ AI-Helper

참고문헌 (33)

이 논문을 인용한 문헌

연구과제 타임라인

활용도 분석정보

활용도 Top5 논문

관련 콘텐츠

원문 보기

원문 URL 링크

오픈액세스(OA) 유형

연관된 기능

이 논문과 함께 이용한 콘텐츠

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트

연합인증

[해외논문] Kick: Shift-N-Overlap Cascades of Transposed Convolutional Layer for Better Autoencoding Reconstruction on Remote Sensing Imagery 원문보기

Abstract ▼ AI-Helper

참고문헌 (33)

이 논문을 인용한 문헌

연구과제 타임라인

전체(0) 논문(0) 특허(0) 보고서(0)

전체(0) 논문(0) 특허(0) 보고서(0)

활용도 분석정보

활용도 Top5 논문 더보기

관련 콘텐츠

원문 보기

원문 URL 링크

오픈액세스(OA) 유형

연관된 기능

이 논문과 함께 이용한 콘텐츠

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트

활용도 Top5 논문