Related Experiment Video
Updated: Jun 9, 2025
13:19
Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
9.0K
LDF-BNN: A Real-Time and High-Accuracy Binary Neural Network Accelerator Based on the Improved BNext.
Rui Wan1,2, Rui Cen1,2, Dezheng Zhang1,2
1Institute of Information Science, Beijing Jiaotong University, Beijing 100044, China.
Micromachines
|October 26, 2024
Summary
This study introduces a Binary Neural Network (BNN) with layered data fusion (LDF-BNN) to improve industrial defect detection accuracy while reducing computational costs. The LDF-BNN achieves high performance on ImageNet and defect detection tasks, making it suitable for edge devices.
Area of Science:
- Computer Vision
- Machine Learning
- Hardware Acceleration
Background:
- Deep Neural Networks (DNNs) excel at feature extraction for industrial defect detection but are computationally intensive for edge devices.
- Traditional Binary Neural Networks (BNNs) offer efficiency but suffer from accuracy degradation.
Purpose of the Study:
- To develop an efficient Binary Neural Network (BNN) with a layered data fusion (LDF) mechanism to address accuracy and computational challenges in industrial defect detection.
- To design a hardware accelerator architecture optimized for the proposed LDF-BNN.
Main Methods:
- Constructed a Layered Data Fusion BNN (LDF-BNN) based on BNext, incorporating a layered data fusion mechanism to minimize bandwidth pressure and accuracy loss.
- Designed an efficient hardware accelerator architecture featuring multi-storage parallelism to enhance computational efficiency and performance for complex BNN models.
Main Results:
- The LDF-BNN achieved 72.23% accuracy, 72.6 FPS, and 1826 GOPs on the ImageNet dataset.
- Demonstrated high applicability to industrial defect detection, achieving 98.70% accuracy on the Mixed WM-38 dataset.
- Outperformed existing methods in comprehensive comparisons, balancing accuracy and computational efficiency.
Conclusions:
- The proposed LDF-BNN effectively mitigates accuracy degradation issues in BNNs while maintaining low computational and memory requirements.
- The developed hardware accelerator architecture enhances the performance of LDF-BNN models, making them suitable for real-time industrial defect detection on edge devices.
