TOWARDS DISTILLATION OF DEEP NEURAL NETWORKS FOR SATELLITE ON-BOARD IMAGE SEGMENTATION
Cubesats platforms expansion increases the need to simplify payloads and to optimize downlink data capabilities. A promising solution is to enhance on-board software, in order to take early decisions, automatically. However, the most efficient methods for data analysis are generally large deep neura...
Main Authors: | F. de Vieilleville, A. Lagrange, R. Ruiloba, S. May |
---|---|
Format: | Article |
Language: | English |
Published: |
Copernicus Publications
2020-08-01
|
Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
Online Access: | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B2-2020/1553/2020/isprs-archives-XLIII-B2-2020-1553-2020.pdf |
Similar Items
-
Urban areas analysis using satellite image segmentation and deep neural network
by: Khryaschev Vladimir, et al.
Published: (2019-01-01) -
Towards On-Board Hyperspectral Satellite Image Segmentation: Understanding Robustness of Deep Learning through Simulating Acquisition Conditions
by: Jakub Nalepa, et al.
Published: (2021-04-01) -
Cloud and Snow Segmentation in Satellite Images Using an Encoder–Decoder Deep Convolutional Neural Networks
by: Kai Zheng, et al.
Published: (2021-07-01) -
Head Network Distillation: Splitting Distilled Deep Neural Networks for Resource-Constrained Edge Computing Systems
by: Yoshitomo Matsubara, et al.
Published: (2020-01-01) -
Layer Leveled Knowledge Distillation for Deep Neural Network Learning
by: LIN, SHIH-CHIEH, et al.
Published: (2018)