Intra-class Structure Aware Networks for Screen Defect Detection
Typically, screen defect detection treats different types of defects as a single category and ignores the large variation among them, which may pose large difficulty to the model learning and thus lead to inferior performance. In this paper, we propose a novel network model, called Intra-class Structure Aware Networks (ISANs), to alleviate the difficulty of learning one single concept which exhibits in various forms. The proposed model introduces more neural units for the “defect” category rather than a single one, to accommodate the large variations in this category, which can significantly improve the representation power. Regularized by prior distribution of intra-class variants, our approach can learn intra-class structure of screen defect without extra fine-grained labels. Experimental results demonstrate that ISANs can effectively discriminate intra-class variants and gain significant performance improvement on screen defect detection task as well as the classification task in MNIST.
KeywordsIntra-class Structure Aware Convolutional Neural Networks Screen defect detection
This work is supported by National Natural Science Foundation of China (61572428,U1509206), Fundamental Research Funds for the Central Universities (2017FZA5014), National Key Research and Development Program (2016YFB1200203) and Key Research and Development Program of Zhejiang Province (2018C01004).
- 2.He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778. IEEE (2016)Google Scholar
- 4.Huang, G., Liu, Z., Weinberger, K.Q., van der Maaten, L.: Densely connected convolutional networks. In: CVPR. IEEE (2017)Google Scholar
- 5.Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: NIPS, pp. 2017–2025. NIPS (2015)Google Scholar
- 6.Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1097–1105. NIPS (2012)Google Scholar
- 7.Laptev, D., Savinov, N., Buhmann, J.M., Pollefeys, M.: Ti-POOLING: transformation-invariant pooling for feature learning in convolutional neural networks. In: CVPR, pp. 289–297. IEEE (2016)Google Scholar
- 8.LeCun, Y., et al.: Handwritten digit recognition with a back-propagation network. In: NIPS, pp. 396–404. NIPS (1990)Google Scholar
- 10.Qiao, S., Liu, C., Shen, W., Yuille, A.: Few-shot image recognition by predicting parameters from activations. arXiv preprint arXiv:1706.03466 (2017)
- 11.Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. In: NIPS, pp. 3859–3869. NIPS (2017)Google Scholar
- 12.Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
- 14.Szegedy, C., et al.: Going deeper with convolutions. In: CVPR, pp. 1–9. IEEE (2015)Google Scholar
- 15.Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning requires rethinking generalization. arXiv preprint arXiv:1611.03530 (2016)