TY - GEN
T1 - Compact Neural Architecture Search for Local Climate Zones Classification
AU - Traore, Kalifou Rene
AU - Camero, Andrés
AU - Zhu, Xiao Xiang
N1 - Publisher Copyright:
© 2021 ESANN Intelligence and Machine Learning. All rights reserved.
PY - 2021
Y1 - 2021
N2 - State-of-the-art Computer Vision models achieve impressive performance but with an increasing complexity. Great advances have been made towards automatic model design, but accounting for model performance and low complexity is still an open challenge. In this study, we propose a neural architecture search strategy for high performance low complexity classification models, that combines an efficient search algorithm with mechanisms for reducing complexity. We tested our proposal on a real World remote sensing problem, the Local Climate Zone classification. The results show that our proposal achieves state-of-the-art performance, while being at least 91.8% more compact in terms of size and FLOPs.
AB - State-of-the-art Computer Vision models achieve impressive performance but with an increasing complexity. Great advances have been made towards automatic model design, but accounting for model performance and low complexity is still an open challenge. In this study, we propose a neural architecture search strategy for high performance low complexity classification models, that combines an efficient search algorithm with mechanisms for reducing complexity. We tested our proposal on a real World remote sensing problem, the Local Climate Zone classification. The results show that our proposal achieves state-of-the-art performance, while being at least 91.8% more compact in terms of size and FLOPs.
UR - http://www.scopus.com/inward/record.url?scp=85129278198&partnerID=8YFLogxK
U2 - 10.14428/esann/2021.ES2021-55
DO - 10.14428/esann/2021.ES2021-55
M3 - Conference contribution
AN - SCOPUS:85129278198
T3 - ESANN 2021 Proceedings - 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
SP - 393
EP - 398
BT - ESANN 2021 Proceedings - 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
PB - i6doc.com publication
T2 - 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2021
Y2 - 6 October 2021 through 8 October 2021
ER -