# GnetDet: Object Detection Optimized on a 224mW CNN Accelerator Chip at the Speed of 106FPS

arXiv: https://arxiv.org/abs/2103.15756 · HTML: https://mlsanity.com/paper/2103.15756/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 27 references that are in the map.
- First posted on arXiv 19 Feb 2021.

## Builds on (most cited first, 18 of 18)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Super Characters: A Conversion from Sentiment Classification to Image Classification](https://mlsanity.com/paper/1810.07653/) (2018)
- [Squared English Word: A Method of Generating Glyph to Use Super Characters for Sentiment Analysis](https://mlsanity.com/paper/1902.02160/) (2019)
- [MRAM Co-designed Processing-in-Memory CNN Accelerator for Mobile and IoT Applications](https://mlsanity.com/paper/1811.12179/) (2018)
- [Ultra Power-Efficient CNN Domain Specific Accelerator with 9.3TOPS/Watt for Mobile and Embedded Applications](https://mlsanity.com/paper/1805.00361/) (2018)
- [System Demo for Transfer Learning across Vision and Text using Domain Specific CNN Accelerator for On-Device NLP Applications](https://mlsanity.com/paper/1906.01145/) (2019)
- [Multi-modal Sentiment Analysis using Super Characters Method on Low-power CNN Accelerator Device](https://mlsanity.com/paper/2001.10179/) (2020)
- [SuperChat: Dialogue Generation by Transfer Learning from Vision to Language using Two-dimensional Word Embedding and Pretrained ImageNet CNN Models](https://mlsanity.com/paper/1905.05698/) (2019)
- [SuperCaptioning: Image Captioning Using Two-dimensional Word Embedding](https://mlsanity.com/paper/1905.10515/) (2019)
- [SuperOCR: A Conversion from Optical Character Recognition to Image Captioning](https://mlsanity.com/paper/2012.02033/) (2020)
- [GnetSeg: Semantic Segmentation Model Optimized on a 224mW CNN Accelerator Chip at the Speed of 318FPS](https://mlsanity.com/paper/2101.10444/) (2021)

## Built on by (most cited first, 1 of 1)

- [Designing Object Detection Models for TinyML: Foundations, Comparative Analysis, Challenges, and Emerging Solutions](https://mlsanity.com/paper/2508.08352/) (2025)

## Abstract (arXiv)

Object detection is widely used on embedded devices. With the wide availability of CNN (Convolutional Neural Networks) accelerator chips, the object detection applications are expected to run with low power consumption, and high inference speed. In addition, the CPU load is expected to be as low as possible for a CNN accelerator chip working as a co-processor with a host CPU. In this paper, we optimize the object detection model on the CNN accelerator chip by minimizing the CPU load. The resulting model is called GnetDet. The experimental result shows that the GnetDet model running on a 224mW chip achieves the speed of 106FPS with excellent accuracy.