Hyperspectral Classification Based on Lightweight 3-D-CNN With Transfer Learning
- Submitting institution
-
Aberystwyth University / Prifysgol Aberystwyth
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 29354750
- Type
- D - Journal article
- DOI
-
10.1109/TGRS.2019.2902568
- Title of journal
- IEEE Transactions on Geoscience and Remote Sensing
- Article number
- -
- First page
- 5813
- Volume
- 57
- Issue
- 8
- ISSN
- 0196-2892
- Open access status
- Compliant
- Month of publication
- April
- Year of publication
- 2019
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
5
- Research group(s)
-
-
- Citation count
- 20
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Presents novel end-to-end 3D lightweight convolutional neural networks for limited samples-based image classification. Work done through international collaboration (UK, Australia and China). Published in IEEE-TGRS, the premier journal in the applied field. Attracted grant awards both before and after publication, from RAEng, British Council, Welsh Government and NSFC. Despite recency, it has led to significant further developments globally, including research conducted by world-leading groups in the area (e.g., Technical U Munich, Germany; Extremadura U, Spain; CAS, China; Melbourne U, Australia; Vrije Universiteit Brussel, Belgium; Arctic U, Norway; National Institute of Advanced Industrial S&T, Japan; Mississippi State U, USA).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -