mlsanityData to 14 Oct 2026

ELASTIC: Efficient Once For All Iterative Search for Object Detection on Microcontrollers

arXiv 2503.21999 ↗First posted 27 Mar 2025cs.CV cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Deploying high-performance object detectors on TinyML platforms poses significant challenges due to tight hardware constraints and the modular complexity of modern detection pipelines. Neural Architecture Search (NAS) offers a path toward automation, but existing methods either restrict optimization to individual modules, sacrificing cross-module synergy, or require global searches that are computationally intractable. We propose ELASTIC (Efficient Once for AlL IterAtive Search for ObjecT DetectIon on MiCrocontrollers), a unified, hardware-aware NAS framework that alternates optimization across modules (e.g., backbone, neck, and head) in a cyclic fashion. ELASTIC introduces a novel Population Passthrough mechanism in evolutionary search that retains high-quality candidates between search stages, yielding faster convergence, up to an 8% final mAP gain, and eliminates search instability observed without population passthrough. In a controlled comparison, empirical results show ELASTIC achieves +4.75% higher mAP and 2x faster convergence than progressive NAS strategies on SVHN, and delivers a +9.09% mAP improvement on PascalVOC given the same search budget. ELASTIC achieves 72.3% mAP on PascalVOC, outperforming MCUNET by 20.9% and TinyissimoYOLO by 16.3%. When deployed on MAX78000/MAX78002 microcontrollers, ELASTICderived models outperform Analog Devices' TinySSD baselines, reducing energy by up to 71.6%, lowering latency by up to 2.4x, and improving mAP by up to 6.99 percentage points across multiple datasets. The experimental videos and codes are available on the project website (https://nail-uh.github.io/elastic.github.io/).

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 21 of its 31 references that are in the map. First posted on arXiv 27 Mar 2025.

Builds on

21 of 31 references.

References · 21

  1. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  2. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  3. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  4. 2018YOLOv3: An Incremental Improvementcited by 2,659
  5. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  6. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 909
  7. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
  8. 2019NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detectioncited by 291
  9. 2020MCUNet: Tiny Deep Learning on IoT Devicescited by 273
  10. 2021MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learningcited by 89
  11. 2021LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Searchcited by 82
  12. 2019DetNAS: Backbone Search for Object Detectioncited by 81
9 more
  1. 2020DORY: Automatic End-to-End Deployment of Real-World DNNs on Low-Cost IoT MCUscited by 58
  2. 2020MobileDets: Searching for Object Detection Architectures for Mobile Acceleratorscited by 55
  3. 2019NAS-FCOS: Fast Neural Architecture Search for Object Detectioncited by 53
  4. 2020Hit-Detector: Hierarchical Trinity Architecture Search for Object Detectioncited by 32
  5. 2023TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Object Detection Network for Low Power Microcontrollerscited by 18
  6. 2023Flexible and Fully Quantized Ultra-Lightweight TinyissimoYOLO for Ultra-Low-Power Edge Systemscited by 11
  7. 2023MCUFormer: Deploying Vision Transformers on Microcontrollers with Limited Memorycited by 9
  8. 2022BED: A Real-Time Object Detection System for Edge Devicescited by 6
  9. 2023DetOFA: Efficient Training of Once-for-All Networks for Object Detection Using Path Filtercited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025TrashDet: Iterative Neural Architecture Search for Efficient Waste Detectioncited by 0
  2. 2026XiYOLO: Energy-Aware Object Detection via Iterative Architecture Search and Scalingcited by 0
  3. 2026ENAS: An Efficient Hardware-Aware Neural Architecture Search Framework for TinyML on Resource-Constrained Microcontrollerscited by 0