Yan XIA, Chen LUO, Yijun ZHOU, Lei JIA. A lightweight deep learning model for TFT-LCD circuits defect classification based on swin transformer[J]. Optics and Precision Engineering, 2023, 31(22): 3357
- Optics and Precision Engineering
- Vol. 31, Issue 22, 3357 (2023)
Fig. 1. Architecture of Swin-T model
Fig. 2. Architecture of Swin Transformer Block
Fig. 3. Token merging module
Fig. 4. Token merging for visualization
Fig. 5. Conventional convolution and depthwise separable convolution
Fig. 6. Knowledge distillation flow
Fig. 7. Loss curve
Fig. 8. Different effect of the parameters T on the model accuracy
Fig. 9. Different effect of the parameters α on the model accuracy at T =3
Fig. 10. Comparison of detection performance between ResNet-34 model and the improved model
Fig. 11. Detection results of the modified model
|
Table 1. Results of parameter n affects experiments
|
Table 2. Results of ablation experiments
|
Table 3. Results of comparison experiments
|
Table 4. Results of comparison experiments on public dataset
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20