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

Source: [Scalable Object Detection on Embedded Devices Using Weight Pruning and Singular Value Decomposition](<https://www.sota2.com/research/paper/68fa6ec61e209131cea41fdf>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:05:49.615Z

Authors: Dohyun Ham, Jaeyeop Jeong, June-Kyoo Park, Raehyeon Jeong, Seungmin Jeon, Hyeongjun Jeon, Yewon Lim

Published: 2023-03-05T18:02:54.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2303.02735>)

[PDF](<https://arxiv.org/pdf/2303.02735.pdf>)