LANDSCAPE OF NEURAL ARCHITECTURE SEARCH ACROSS SENSORS: HOW MUCH DO THEY DIFFER?

Abstract. With the rapid rise of neural architecture search, the ability to understand its complexity from the perspective of a search algorithm is desirable. Recently, Traoré et al. have proposed the framework of Fitness Landscape Footprint to help describe and compare neural architecture search problems. It attempts at describing why a search strategy might be successful, struggle or fail on a target task. Our study leverages this methodology in the context of searching across sensors, including sensor data fusion. In particular, we apply the Fitness Landscape Footprint to the real-world image classification problem of So2Sat LCZ42, in order to identify the most beneficial sensor to our neural network hyper-parameter optimization problem. From the perspective of distributions of fitness, our findings indicate a similar behaviour of the CNN search space for all sensors: the longer the training time, the larger the overall fitness, and more flatness in the landscapes (less ruggedness and deviation). Regarding sensors, the better the fitness they enable (Sentinel-2), the better the search trajectories (smoother, higher persistence). Results also indicate very similar search behaviour for sensors that can be decently fitted by the search space (Sentinel-2 and fusion).

Angaben zum Objekt

• Standort: Deutsche Nationalbibliothek Frankfurt am Main
• Umfang: Online-Ressource
• Sprache: Englisch

Verweise und Beziehungen

• Erschienen in: LANDSCAPE OF NEURAL ARCHITECTURE SEARCH ACROSS SENSORS: HOW MUCH DO THEY DIFFER? ; volume:V-3-2022 ; year:2022 ; pages:217-224 ; extent:8 ; ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences ; V-3-2022 (2022), 217-224 (gesamt 8)

Beteiligte, Orts- und Zeitangaben

• Urheber: Traoré, K. R. ; Camero, A. ; Zhu, X. X.

Weitere Informationen

• DOI: 10.5194/isprs-annals-V-3-2022-217-2022
• URN: urn:nbn:de:101:1-2022051905290871017341
• Rechteinformation: Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
• Letzte Aktualisierung: 15.08.2025, 07:33 MESZ