mlsanityData to 14 Oct 2026

STResNet & STYOLO : A New Family of Compact Classification and Object Detection Models for MCUs

arXiv 2601.05364 ↗First posted 8 Jan 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent advancements in lightweight neural networks have significantly improved the efficiency of deploying deep learning models on edge hardware. However, most existing architectures still trade accuracy for latency, which limits their applicability on microcontroller and neural processing unit based devices. In this work, we introduce two new model families, STResNet for image classification and STYOLO for object detection, jointly optimized for accuracy, efficiency, and memory footprint on resource constrained platforms. The proposed STResNet series, ranging from Nano to Tiny variants, achieves competitive ImageNet 1K accuracy within a four million parameter budget. Specifically, STResNetMilli attains 70.0 percent Top 1 accuracy with only three million parameters, outperforming MobileNetV1 and ShuffleNetV2 at comparable computational complexity. For object detection, STYOLOMicro and STYOLOMilli achieve 30.5 percent and 33.6 percent mean average precision, respectively, on the MS COCO dataset, surpassing YOLOv5n and YOLOX Nano in both accuracy and efficiency. Furthermore, when STResNetMilli is used as a backbone with the Ultralytics training environment.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 27 references that are in the map. First posted on arXiv 8 Jan 2026.

Builds on

20 of 27 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  5. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  6. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  7. 2019Searching for MobileNetV3cited by 1,994
  8. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  9. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,200
  10. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,136
  11. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,101
  12. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,071
8 more
  1. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
  2. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
  3. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 673
  4. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 485
  5. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 479
  6. 2014Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluationcited by 306
  7. 2014Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decompositioncited by 203
  8. 2015Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applicationscited by 162

Built on by

Not cited yet.