• Home
  • Search
  • Efficient Mixed-Type Wafer Defect Pattern Recognition Based on Light-Weight Neural Network.
  • Cite Icon15
  • https://doi.org/10.3390/mi15070836Copy DOI Icon

Efficient Mixed-Type Wafer Defect Pattern Recognition Based on Light-Weight Neural Network.

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Wafer defect pattern recognition can help engineers improve the production process of semiconductor chips. In real industrial scenarios, the recognition of mixed-type wafer defects is difficult and the production scale of semiconductor wafers is large, which requires high accuracy and speed in wafer defect pattern recognition. This study proposes a light-weight neural network model to efficiently recognize mixed-type wafer defects. The proposed model is constructed via inverted residual convolution blocks with attention mechanisms and large kernel convolution downsampling layers. The inference speed of the inverted residual convolution block is fast, and the attention mechanism can enhance feature extraction capabilities. Large kernel convolutions help the network retain more important feature information during downsampling operations. The experimental results on the real Mixed-type WM38 dataset show that the proposed model achieves a recognition accuracy of 98.69% with only 1.01 M parameters. Compared with some popular high-performance models and light-weight models, our model has advantages in both recognition accuracy and inference speed. Finally, we deploy the model as a TensorRT engine, which significantly improves the inference speed of the model, enabling it to process more than 1300 wafer maps per second.

Loading PDF

Similar Papers
  • Research Article
  • Citations1

Lightweight deep models based on domain adaptation and network pruning for breast cancer HER2 scoring: IHC vs. H&E histopathological images

  • Sep 15, 2025
  • PLOS One
  • Lamiaa Abdel-Hamid +2
  • Research Article
  • Citations13

Flower image classification based on an improved lightweight neural network with multi-scale feature fusion and attention mechanism.

  • Jan 01, 2023
  • Mathematical Biosciences and Engineering
  • Zhigao Zeng +4
  • Research Article
  • Citations6

Research on Improved Lightweight YOLOv5s for Multi-Scale Ship Target Detection

  • Jul 12, 2024
  • Applied Sciences
  • Peng Zhang +6
  • Conference Article
  • Citations4

Occluded Face Recognition Algorithm Incorporating Attention Mechanism

  • Jan 12, 2024
  • Yibo Li +2
  • Research Article
  • Citations55

Heart Sounds Classification Based on Feature Fusion Using Lightweight Neural Networks

  • Jan 01, 2021
  • IEEE Transactions on Instrumentation and Measurement
  • Suyi Li +3
  • Research Article
  • Citations18

Optimization of YOLOv7 Based on PConv, SE Attention and Wise-IoU

  • Mar 01, 2024
  • International Journal of Computational Intelligence and Applications
  • Liu Zhigang +2
  • Conference Article

Research on Facial Expression Recognition Algorithm Based on Attention Mechanism and Lightweight Neural Network

  • Apr 26, 2024
  • Xiaoping Tang +1
  • Research Article
  • Citations7

LiteMixer: Cauliflower Disease Diagnosis based on a Novel Lightweight Neural Network

  • Feb 02, 2024
  • The Computer Journal
  • Yi Zhong +2
  • Conference Article
  • Citations1

Attention-based Efficient Lightweight Model for Accurate Real-Time Face Verification on Embedded Device

  • Apr 23, 2021
  • Dongmei Wei +4
  • Research Article
  • Citations8

Improving YOLOv4-Tiny’s Construction Machinery and Material Identification Method by Incorporating Attention Mechanism

  • Apr 26, 2022
  • Mathematics
  • Jiale Yao +3
  • Book Chapter

Model-Efficient TTS

  • Jan 01, 2023
  • Xu Tan
  • Conference Article
  • Citations2

Residual Attention Block Search for Lightweight Image Super-Resolution

  • Jul 05, 2021
  • Wenrui Liao +3
  • Research Article
  • Citations11

Lightweight deep learning model incorporating an attention mechanism and feature fusion for automatic classification of gastric lesions in gastroscopic images.

  • Aug 11, 2023
  • Biomedical Optics Express
  • Lingxiao Wang +3
  • PDF
  • Research Article
  • Citations3

A neural architecture search optimized lightweight attention ensemble model for nutrient deficiency and severity assessment in diverse crop leaves

  • Oct 27, 2025
  • Scientific Reports
  • Sudhakar Muthusamy +1
  • Research Article

A Lightweight Model for Hot-Rolled Steel Strip Surface Defect Recognition.

  • Mar 04, 2026
  • Sensors (Basel, Switzerland)
  • Naixuan Guo +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.