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

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

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.

• Jezik: Angleški jezik
• Ključne besede: adaptive inference, energy-efficient deep learning, image segmentation, precision agriculture, slimmable neural networks, unmanned aerial vehicles, weed detection
• Vrsta gradiva: Članek v reviji
• Tipologija: 1.01 - Izvirni znanstveni članek
• Organizacija: FRI - Fakulteta za računalništvo in informatiko
• Status publikacije: Objavljeno
• Različica publikacije: Objavljena publikacija
• Leto izida: 2026
• Št. strani: Str. 116854-116866
• Številčenje: Vol. 14
• PID: 20.500.12556/RUL-186076
• UDK: 004.93:004.8:632.51
• ISSN pri članku: 2169-3536
• DOI: 10.1109/ACCESS.2026.3718374
• COBISS.SI-ID: 288258307
• Datum objave v RUL: 26.08.2026

Gradivo je del revije

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

Licence

• Licenca: CC BY 4.0, Creative Commons Priznanje avtorstva 4.0 Mednarodna
• Povezava: http://creativecommons.org/licenses/by/4.0/deed.sl
• Opis: To je standardna licenca Creative Commons, ki daje uporabnikom največ možnosti za nadaljnjo uporabo dela, pri čemer morajo navesti avtorja.

Sekundarni jezik

• Jezik: Slovenski jezik
• Ključne besede: prilagodljivo sklepanje, energijsko učinkovito globoko učenje, segmentacija slik, precizno kmetijstvo, nevronske mreže s prilagodljivo širino, brezpilotni zrakoplovi, zaznavanje plevela