IEEE IGARSS 2021 || Brussels, Belgium || July 12–14, 2021 • Physical

FR4.O-13.3

INVESTIGATING THE IMPACT OF THE TRAINING SET SIZE ON DEEP LEARNING-POWERED HYPERSPECTRAL UNMIXING

Lukasz Tulczyjew, KP Labs, Poland; Jakub Nalepa, KP Labs / Silesian University of Technology, Poland

Session:

Machine Learning with Small Earth Observation Datasets

Track:

Invited Sessions

Presentation Time:

Fri, 16 Jul, 15:10-15:25 (UTC)
Fri, 16 Jul, 17:10-17:25 Central Europe Summer Time (UTC +2)
Fri, 16 Jul, 23:10-23:25 China Standard Time (UTC +8)
Fri, 16 Jul, 11:10-11:25 Eastern Daylight Time (UTC -4)

Session Co-Chairs:

Matthieu Molinier, VTT Technical Research Centre of Finland Ltd and Hanna Meyer, University of Münster

Session Manager:

Songyao Huai

Session FR4.O-13

FR4.O-13.1: The trap of random sampling and how to avoid it - Alternative sampling strategies for a realistic estimate of the generalization error in remote sensing

Ronny Hänsch, German Aerospace Center (DLR), Germany

FR4.O-13.3: INVESTIGATING THE IMPACT OF THE TRAINING SET SIZE ON DEEP LEARNING-POWERED HYPERSPECTRAL UNMIXING

Lukasz Tulczyjew, KP Labs, Poland; Jakub Nalepa, KP Labs / Silesian University of Technology, Poland

FR4.O-13.4: ESTIMATING THE AREA OF APPLICABILITY OF REMOTE SENSING-BASED MACHINE LEARNING MODELS WITH LIMITED TRAINING DATA

Hanna Meyer, Edzer Pebesma, University of Münster, Germany

FR4.O-13.5: TRUSTING SMALL TRAINING DATASET FOR SUPERVISED CHANGE DETECTION

Sudipan Saha, Technical University of Munich, Germany; Biplab Banerjee, Indian Institute of Technology Bombay, India; Xiao Xiang Zhu, German Aerospace Center (DLR), Germany

FR4.O-13.6: PATCH SIZE SELECTION FOR ANALYSIS OF SUB-METER RESOLUTION HYPERSPECTRAL IMAGERY OF FORESTS

Matti Mõttus, Matthieu Molinier, Eelis Halme, VTT Technical Research Centre of Finland, Finland; Hai Cu, Jorma Laaksonen, Aalto University, Finland

INVESTIGATING THE IMPACT OF THE TRAINING SET SIZE ON DEEP LEARNING-POWERED HYPERSPECTRAL UNMIXING

Quicklinks

Downloads