RADLER : context-aware slimmable model selection for energy-efficient real-time UAV weed detection

Machidon, Alina Luminita (author), Krašovec, Andraž (author), Igreţ, Ioana C. (author), Pejović, Veljko (author), Machidon, Octavian-Mihai (author)

Real-time UAV weed detection must operate under tight onboard compute and energy constraints, yet most lightweight segmentation pipelines still commit the system to a single fixed accuracy-efficiency operating point. This article introduces RADLER, a context-aware model selection strategy for slimmable neural networks that predicts, for each input image, the smallest network width that remains close to the best attainable segmentation quality. RADLER combines image-level contextual features, feature scaling with redundancy diagnostics, and threshold-controlled optimal-width labels to expose multiple operating points rather than a single adaptive configuration. We evaluate the method on two public UAV weed detection datasets, compare it against static-width baselines and an oracle reference, and characterize runtime and energy behavior on an NVIDIA Jetson Nano. Across the evaluated settings, RADLER matches full-width performance within uncertainty in one setting and otherwise trades a small, measurable IoU decrease for lower average selected width, enabling energy savings between 25% and 50% depending on the operating point. The results show that context-aware slimmable model selection can make onboard agricultural vision pipelines more transparent in their trade-offs and better suited to battery-constrained UAV platforms.

• Language: English
• Keywords: adaptive inference, energy-efficient deep learning, image segmentation, precision agriculture, slimmable neural networks, unmanned aerial vehicles, weed detection
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FRI - Faculty of Computer and Information Science
• Publication status: Published
• Publication version: Version of Record
• Year: 2026
• Number of pages: Str. 116854-116866
• Numbering: Vol. 14
• PID: 20.500.12556/RUL-186076
• UDC: 004.93:004.8:632.51
• ISSN on article: 2169-3536
• DOI: 10.1109/ACCESS.2026.3718374
• COBISS.SI-ID: 288258307
• Publication date in RUL: 26.08.2026

Record is a part of a journal

• Title: IEEE access
• Publisher: Institute of Electrical and Electronics Engineers
• ISSN: 2169-3536
• COBISS.SI-ID: 519839513

Licences

• License: CC BY 4.0, Creative Commons Attribution 4.0 International
• Link: http://creativecommons.org/licenses/by/4.0/
• Description: This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Secondary language

• Language: Slovenian
• Keywords: prilagodljivo sklepanje, energijsko učinkovito globoko učenje, segmentacija slik, precizno kmetijstvo, nevronske mreže s prilagodljivo širino, brezpilotni zrakoplovi, zaznavanje plevela