Tell a friend
Print
Demir, Emre and Traoré, Kalifou René and Camero, Andres (2024) Leveraging performance-based metadata for designing multi-objective NAS strategies for efficient models in Earth Observation. In: ESANN 2024 Proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, pp. 209-214. www.i6doc.com/en/. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, 2024-10-09 - 2024-10-11, Brugge, Belgium. doi: 10.14428/esann/2024.ES2024-94. ISBN 978-2-87587-090-2.
![[img]](https://elib.dlr.de/style/images/fileicons/application_pdf.png) |
PDF
1MB |
Official URL: https://i6doc.com/en/info/?id=6
Abstract
Earth Observational (EO) datasets present challenges that differ from traditional Computer Vision benchmarks often examined by the AutoML community. To assist EO researchers in leveraging AutoML techniques, we offer a NAS benchmark with performance meta-data specifically for an EO context. This dataset not only focuses on resource-efficient models crucial to EO but also includes hardware-based metrics. Moreover, we investigate performance prediction to build a data-centric approach for initializing multi-objective NAS search algorithms.
| Item URL in elib: | https://elib.dlr.de/207631/ | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Document Type: | Conference or Workshop Item (Poster) | ||||||||||||||||
| Title: | Leveraging performance-based metadata for designing multi-objective NAS strategies for efficient models in Earth Observation | ||||||||||||||||
| Authors: |
| ||||||||||||||||
| Date: | 2024 | ||||||||||||||||
| Journal or Publication Title: | ESANN 2024 Proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning | ||||||||||||||||
| Refereed publication: | Yes | ||||||||||||||||
| Open Access: | Yes | ||||||||||||||||
| Gold Open Access: | No | ||||||||||||||||
| In SCOPUS: | No | ||||||||||||||||
| In ISI Web of Science: | No | ||||||||||||||||
| DOI: | 10.14428/esann/2024.ES2024-94 | ||||||||||||||||
| Page Range: | pp. 209-214 | ||||||||||||||||
| Publisher: | www.i6doc.com/en/ | ||||||||||||||||
| ISBN: | 978-2-87587-090-2 | ||||||||||||||||
| Status: | Published | ||||||||||||||||
| Keywords: | AutoML. Neural Architecture Search, Multi-objective, Benchmark, Earth Observation | ||||||||||||||||
| Event Title: | European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning | ||||||||||||||||
| Event Location: | Brugge, Belgium | ||||||||||||||||
| Event Type: | international Conference | ||||||||||||||||
| Event Start Date: | 9 October 2024 | ||||||||||||||||
| Event End Date: | 11 October 2024 | ||||||||||||||||
| HGF - Research field: | Aeronautics, Space and Transport | ||||||||||||||||
| HGF - Program: | Space | ||||||||||||||||
| HGF - Program Themes: | Earth Observation | ||||||||||||||||
| DLR - Research area: | Raumfahrt | ||||||||||||||||
| DLR - Program: | R EO - Earth Observation | ||||||||||||||||
| DLR - Research theme (Project): | R - Artificial Intelligence, R - Optical remote sensing | ||||||||||||||||
| Location: | Oberpfaffenhofen | ||||||||||||||||
| Institutes and Institutions: | Remote Sensing Technology Institute > EO Data Science | ||||||||||||||||
| Deposited By: | Traoré, Mr René | ||||||||||||||||
| Deposited On: | 23 Oct 2024 09:25 | ||||||||||||||||
| Last Modified: | 11 Nov 2024 08:52 |
Repository Staff Only: item control page
