[1] R M HARALICK, K SHANMUGAM, I DINSTEIN. Textural features for image classification. IEEE Transactions on Systems， Man， and Cybernetics, 610-621(1973).

[2] N DALAL, B TRIGGS. Histograms of oriented gradients for human detection, 886-893(20).

[3] G STOCKMAN, LG SHAPIRO. Computer Vision, 69-73(2002).

[4] J C PLATT(1998).

[5] S B KANG, J H LEE, K Y SONG et al. Automatic defect classification of TFT-LCD panels using machine learning, 2175-2177(5).

[6] W HUANG, H T LU. Defect Classification of TFT-LCD with bag of visual words approach, 167-170(27).

[7] L F KONG, J SHEN, Z L HU et al. Detection of Water-Stains defects in TFT-LCD based on machine vision, 1-5(13).

[8] 肖术明， 王绍举， 常琳， 等. 面向手写数字图像的压缩感知快速分类［J］. 光学 精密工程， 2021， 29（7）： 1709-1719. doi: 10.37188/OPE.20212907.1709XIAOS M， WANGS J， CHANGL， et al. Compressive sensing fast classification for handwritten digital images［J］. Opt. Precision Eng.， 2021， 29（7）： 1709-1719.（in Chinese）. doi: 10.37188/OPE.20212907.1709

[9] 苗传开， 娄树理， 李婷， 等. 基于弱监督学习的多标签红外图像分类算法［J］. 光学 精密工程， 2022， 30（20）： 2501-2509. doi: 10.37188/ope.20223020.2501MIAOC K， LOUS L， LIT， et al. Multi-label infrared image classification algorithm based on weakly supervised learning［J］. Opt. Precision Eng.， 2022， 30（20）： 2501-2509. （in Chinese）. doi: 10.37188/ope.20223020.2501

[10] P CHIKONTWE, S KIM, S H PARK. CAD： Co-Adapting discriminative features for improved Few-Shot classification, 14534-14543(18).

[11] Z ZHANG, Z XUE, Y CHEN et al. Boosting Verified Training for Robust Image Classifications via Abstraction. arXiv, 2303-11552(2023). https：//arxiv.org/abs/2303.11552.pdf

[12] W CHEN, Y GAO, L GAO et al. A new ensemble approach based on deep convolutional neural networks for steel surface defect classification. Procedia CIRP, 72, 1069-1072(2018).

[13] G FU, P SUN, W ZHU et al. A deep-learning-based approach for fast and robust steel surface defects classification. Optics and Lasers in Engineering, 121, 397-405(2019).

[14] I KONOVALENKO, P MARUSCHAK, J BREZINOVÁ et al. Steel surface defect classification using deep residual neural network. Metals, 10, 846(2020).

[15] D HE, K XU, D WANG. Design of multi-scale receptive field convolutional neural network for surface inspection of hot rolled steels. Image and Vision Computing, 89, 12-20(2019).

[16] M HASELMANN, D GRUBER. Supervised machine learning based surface inspection by synthetizing artificial defects, 390-395(18).

[17] Z LIU, Y T LIN, Y CAO et al. Swin transformer： hierarchical vision transformer using shifted windows, 9992-10002(10).

[18] A DOSOVITSKIY, L BEYER, A KOLESNIKOV et al. An image is worth. arXiv, 2010-11929(2020). https：//arxiv.org/abs/2010.11929.pdf

[19] D BOLYA, C FU, X DAI et al. Token Merging： your ViT but Faster. arXiv, 2210-09461(2022). https：//arxiv.org/abs/2210.09461.pdf

[20] F CHOLLET. Xception： deep learning with depthwise separable convolutions, 1800-1807(21).

[21] G HINTON, O VINYALS, J DEAN. Distilling The Knowledge in a Neural Network. arXiv, 1503-02531(2015). https：//arxiv.org/abs/1503.02531.pdf

[22] K M HE, X Y ZHANG, S Q REN et al. Deep residual learning for image recognition, 770-778(27).

[23] G HUANG, Z LIU, L VAN DER MAATEN et al. Densely connected convolutional networks, 2261-2269(21).

[24] M TAN, Q V LE. EfficientNetV2： Smaller Models and Faster Training. arXiv, 2104-00298(2021). https：//arxiv.org/abs/2104.00298.pdf

[25] S MEHTA, M RASTEGARI. Separable Self-Attention for Mobile Vision Transformers. arXiv, 2206-02680(2022). https：//arxiv.org/abs/2206.02680.pdf

[26] Z LIU, H Z MAO, C Y WU et al. A ConvNet for the 2020s, 11966-11976(18).

[27] S DEBNATH, R H HU et al. ConvNeXt V2： Co-Designing and scaling convnets with masked autoencoders, 16133-16142(17).

[28] Y X FANG, W WANG, B H XIE et al. EVA： exploring the limits of masked visual representation learning at scale, 19358-19369(17).

[29] Y FANG, Q SUN, X WANG et al. EVA-02： a Visual Representation for Neon Genesis. arXiv, 2303-11331(2023). https：//arxiv.org/abs/2303.11331.pdf