Trident-LK Net: A Lightweight Trident Structure Network With Large Kernel for Muti-Scale Defect Detection
IEEE ACCESS(2023)
Abstract
Identifying defects at different scales is a challenge in industrial defect detection. To solve this problem, many multi-scale feature fusion networks have been proposed to improve multi-scale target detection accuracy by fusing fine-grained information from shallow networks and semantic information from deep networks. This approach requires the introduction of extraa parameters. Thinking from another perspective, can the accuracy of multi-scale target detection be improved by fusing the feature information under different receptive fields? For this purpose, we designed a three-layer network structure called Trident-LK Net. our model uses convolutional kernels of different sizes (31, 25, 1) in the feature extraction phase and establishes cross-fusion connections. This omits the feature fusion part and greatly reduces the network parameters while obtaining a good detection accuracy. Finally we perform experiments on the neu-det dataset and the gc10 dataset to verify the feasibility of our idea. While keeping the number of parameters to a minimum, our model achieves competitive detection results on the neu-det dataset (76.9% mAP) and optimal on the gc10 dataset (63.55% mAP). Our code will be publicly available at https://github.com/syyang2022/Trident-LK-Net.
MoreTranslated text
Key words
Feature extraction,Convolutional neural networks,Kernel,Computational modeling,Detectors,Data mining,Steel,Industrial engineering,Structural engineering,Convolutional neural network,defect detection,feature fusion,lightweight network
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined