# REQ-YOLO: A Resource-Aware, Efficient Quantization Framework for Object Detection on FPGAs

arXiv: https://arxiv.org/abs/1909.13396 · HTML: https://mlsanity.com/paper/1909.13396/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Sep 2019.

## Built on by (most cited first, 13 of 13)

- [YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection](https://mlsanity.com/paper/2509.25164/) (2025)
- [Teachers Do More Than Teach: Compressing Image-to-Image Models](https://mlsanity.com/paper/2103.03467/) (2021)
- [Binary Complex Neural Network Acceleration on FPGA](https://mlsanity.com/paper/2108.04811/) (2021)
- [A survey on FPGA-based accelerator for ML models](https://mlsanity.com/paper/2412.15666/) (2024)
- [Spectral-DP: Differentially Private Deep Learning through Spectral Perturbation and Filtering](https://mlsanity.com/paper/2307.13231/) (2023)
- [Reducing the Side-Effects of Oscillations in Training of Quantized YOLO Networks](https://mlsanity.com/paper/2311.05109/) (2023)
- [T-RECX: Tiny-Resource Efficient Convolutional neural networks with early-eXit](https://mlsanity.com/paper/2207.06613/) (2022)
- [EfficientBioAI: Making Bioimaging AI Models Efficient in Energy, Latency and Representation](https://mlsanity.com/paper/2306.06152/) (2023)
- [PointSplit: Towards On-device 3D Object Detection with Heterogeneous Low-power Accelerators](https://mlsanity.com/paper/2504.03654/) (2025)
- [Designing Object Detection Models for TinyML: Foundations, Comparative Analysis, Challenges, and Emerging Solutions](https://mlsanity.com/paper/2508.08352/) (2025)
- [Tackling Variabilities in Autonomous Driving](https://mlsanity.com/paper/2104.10415/) (2021)
- [DTNN: Energy-efficient Inference with Dendrite Tree Inspired Neural Networks for Edge Vision Applications](https://mlsanity.com/paper/2105.11848/) (2021)
- [Performance/power assessment of CNN packages on embedded automotive platforms](https://mlsanity.com/paper/2310.08401/) (2023)

## Abstract (arXiv)

Deep neural networks (DNNs), as the basis of object detection, will play a key role in the development of future autonomous systems with full autonomy. The autonomous systems have special requirements of real-time, energy-efficient implementations of DNNs on a power-constrained system. Two research thrusts are dedicated to performance and energy efficiency enhancement of the inference phase of DNNs. The first one is model compression techniques while the second is efficient hardware implementation. Recent works on extremely-low-bit CNNs such as the binary neural network (BNN) and XNOR-Net replace the traditional floating-point operations with binary bit operations which significantly reduces the memory bandwidth and storage requirement. However, it suffers from non-negligible accuracy loss and underutilized digital signal processing (DSP) blocks of FPGAs. To overcome these limitations, this paper proposes REQ-YOLO, a resource-aware, systematic weight quantization framework for object detection, considering both algorithm and hardware resource aspects in object detection. We adopt the block-circulant matrix method and propose a heterogeneous weight quantization using the Alternating Direction Method of Multipliers (ADMM), an effective optimization technique for general, non-convex optimization problems. To achieve real-time, highly-efficient implementations on FPGA, we present the detailed hardware implementation of block circulant matrices on CONV layers and develop an efficient processing element (PE) structure supporting the heterogeneous weight quantization, CONV dataflow and pipelining techniques, design optimization, and a template-based automatic synthesis framework to optimally exploit hardware resource. Experimental results show that our proposed REQ-YOLO framework can significantly compress the YOLO model while introducing very small accuracy degradation.