mlsanityData to 14 Oct 2026

Scalable Object Detection on Embedded Devices Using Weight Pruning and Singular Value Decomposition

arXiv 2303.02735 ↗First posted 5 Mar 2023cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper presents a method for optimizing object detection models by combining weight pruning and singular value decomposition (SVD). The proposed method was evaluated on a custom dataset of street work images obtained from https://universe.roboflow.com/roboflow-100/street-work. The dataset consists of 611 training images, 175 validation images, and 87 test images with 7 classes. We compared the performance of the optimized models with the original unoptimized model in terms of frame rate, mean average precision (mAP@50), and weight size. The results show that the weight pruning + SVD model achieved a 0.724 mAP@50 with a frame rate of 1.48 FPS and a weight size of 12.1 MB, outperforming the original model (0.717 mAP@50, 1.50 FPS, and 12.3 MB). Precision-recall curves were also plotted for all models. Our work demonstrates that the proposed method can effectively optimize object detection models while balancing accuracy, speed, and model size.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 14 references that are in the map. First posted on arXiv 5 Mar 2023.

Builds on

12 of 14 references.

References · 12

  1. 2014Going Deeper with Convolutionscited by 4,241
  2. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  3. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  4. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  5. 2016Pruning Filters for Efficient ConvNetscited by 1,143
  6. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
  7. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 982
  8. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
  9. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 592
  10. 2014Deeply-Supervised Netscited by 367
  11. 2014Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluationcited by 306
  12. 2016Trained Ternary Quantizationcited by 208

Built on by

Not cited yet.