Improving Semi-Supervised Image Classification by Assigning Different Weights to Correctly and Incorrectly Classified Samples
Source abstract
Abstract
Semi-supervised deep learning, a model that aims to effectively use unlabeled data to help learn sample features from labeled data, is a recent hot topic. To effectively use unlabeled data, a new semi-supervised learning model based on a consistency strategy is proposed. In the supervised part with labeled samples, the image generation model first generates some artificial images to complement the limited number of labeled samples. Secondly, the sample label mapping, as the “benchmark”, is compared to the corresponding sample features in the network as an additional loss to complement the original supervisory loss, aiming to better correct the model parameters. Finally, the original supervised loss is changed so that the network parameters are determined by the characteristics of each correctly classified sample. In the unsupervised part, the actual unsupervised loss is altered so that the model does not “treat all samples equally” and can focus more on the characteristics of misclassified samples. A total of 40 labeled samples from the CIFAR-10 and SVHN datasets were used to train the semi-supervised model achieving accuracies of 93.25% and 96.83%, respectively, demonstrating the effectiveness of the proposed semi-supervised model.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Domain Adaptation and Few-Shot Learning · Machine Learning and Data Classification
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
State Key Laboratory of Dynamic Measurement Technology, North University of China, Taiyuan 030051, China
Newcastle University, Newcastle upon Tyne NE1 7RU, UK
Beijing Institute of Technology, Beijing 100081, China
Chengdu University of Technology, Chengdu 610059, China
Yangzhou University, Yangzhou 225012, China
Chengdu University of Information Technology, Chengdu 610225, China
References (48)
Show source-provided references
1. Sun, B.Y., and Huang, D.S. (2004, January 15–19). Texture classification based on support vector machine and wavelet transform. Proceedings of the Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788), Hangzhou, China.
2. Image classification for content-based indexing10.1109/83.892448 ↗
3. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv.
4. Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely connected convolutional networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
5. Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21–26). Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.106 ↗
6. Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A.A. (2017, January 4–9). Inception-v4, inception-resnet and the impact of residual connections on learning. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.10.1609/aaai.v31i1.11231 ↗
7. Girshick, R. (2015, January 11–18). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.169 ↗
8. Analysis of convolutional neural network based image classification techniques
9. HCFNN: High-order coverage function neural network for image classification10.1016/j.patcog.2022.108873 ↗
10. Image segmentation using deep learning: A survey
11. Deep learning techniques for medical image segmentation: Achievements and challenges10.1007/s10278-019-00227-x ↗
12. Object detection with deep learning: A review10.1109/TNNLS.2018.2876865 ↗
13. Recent advances in deep learning for object detection10.1016/j.neucom.2020.01.085 ↗
14. A survey of deep learning-based object detection10.1109/ACCESS.2019.2939201 ↗
15. He, T., Zhang, Z., Zhang, H., Zhang, Z., Xie, J., and Li, M. (2019, January 15–20). Bag of tricks for image classification with convolutional neural networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00065 ↗
16. A survey of image classification methods and techniques for improving classification performance10.1080/01431160600746456 ↗
17. Multi-label active learning algorithms for image classification: Overview and future promise
18. Deep convolutional neural networks for image classification: A comprehensive review10.1162/neco_a_00990 ↗
19. Radford, A., Metz, L., and Chintala, S. (2015). Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. arXiv.
20. Improved Techniques for Training GANs
21. Imran, A.-A.-Z., and Terzopoulos, D. (2019, January 16–19). Multi-adversarial Variational Autoencoder Networks. Proceedings of the 2019 18th IEEE International Conference On Machine Learning and Applications (ICMLA), Boca Raton, FL, USA.10.1109/ICMLA.2019.00137 ↗
22. CCS-GAN: A semi-supervised generative adversarial network for image classification10.1007/s00371-021-02262-8 ↗
23. Aviles-Rivero, A.I., Papadakis, N., Li, R., Sellars, P., Fan, Q., Tan, R.T., and Schönlieb, C.B. (2019, January 13–17). GraphXNET—Chest X-Ray Classification under Extreme Minimal Supervision. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Shenzhen, China.
24. Jiang, B., Zhang, Z., Lin, D., Tang, J., and Luo, B. (2019, January 15–20). Semi-supervised learning with graph learning-convolutional networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.01157 ↗
25. Lee, D.H. (2013, January 16–21). Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. Proceedings of the Workshop on Challenges in Representation Learning, ICML, Atlanta, GA, USA.
26. Laine, S., and Aila, T. (2016). Temporal ensembling for semi-supervised learning. arXiv.
27. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
28. Virtual adversarial training: A regularization method for supervised and semi-supervised learning10.1109/TPAMI.2018.2858821 ↗
29. Certainty driven consistency loss on multi-teacher networks for semi-supervised learning10.1016/j.patcog.2021.108140 ↗
30. Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., and Raffel, C. (2019). Mixmatch: A holistic approach to semi-supervised learning. Adv. Neural Inf. Process. Syst., 32.
31. Unsupervised data augmentation for consistency training
32. Berthelot, D., Carlini, N., Cubuk, E.D., Kurakin, A., Sohn, K., Zhang, H., and Raffel, C. (2019). Remixmatch: Semi-supervised learning with distribution alignment and augmentation anchoring. arXiv.
33. Fixmatch: Simplifying semi-supervised learning with consistency and confidence
34. Generative adversarial nets
35. Mirza, M., and Osindero, S. (2014). Conditional generative adversarial nets. arXiv.
36. Brock, A., Donahue, J., and Simonyan, K. (2018). Large scale GAN training for high fidelity natural image synthesis. arXiv.
37. Odena, A., Olah, C., and Shlens, C.J. (2017, January 15–17). Conditional image synthesis with auxiliary classifier gans. Proceedings of the International Conference on Machine Learning (PMLR 2017), Sydney, Australia.
38. Lin, T.Y., Goyal, P., Girshick, R., He, K., and Dollár, P. (2017, January 22–29). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.324 ↗
39. Sergievskiy, N., and Ponamarev, A. (2019). Reduced focal loss: 1st place solution to xview object detection in satellite imagery. arXiv.
40. Semi-supervised medical image classification with relation-driven self-ensembling model10.1109/TMI.2020.2995518 ↗
41. Zhou, Z., Lu, C., Wang, W., Dang, W., and Gong, K. (2022). Semi-Supervised Medical Image Classification Based on Attention and Intrinsic Features of Samples. Appl. Sci., 12.10.3390/app12136726 ↗
42. Haque, A. (2021, January 22–24). EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and GANs (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, Palo Alto, CA, USA.10.1609/aaai.v35i18.17895 ↗
43. Li, C., Xu, K., Zhu, J., Liu, J., and Zhang, B. (2021). Triple Generative Adversarial Networks. IEEE Trans. Pattern Anal. Mach. Intell.10.1109/TPAMI.2021.3127558 ↗
44. Zagoruyko, S., and Komodakis, N. (2016). Wide residual networks. arXiv.10.5244/C.30.87 ↗
45. Rectifier nonlinearities improve neural network acoustic models
46. Ioffe, S., and Szegedy, C. (2015, January 20–22). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the International Conference on Machine Learning (PMLR 2015), Hong Kong, China.
47. Krizhevsky, A., Nair, V., and Hinton, G. (2022, September 25). The CIFAR-10 Dataset. 2014, Volume 55. Available online: https://www.cs.toronto.edu/~kriz/cifar.html.
48. Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., and Ng, A.Y. (2011, January 12–17). Reading digits in natural images with unsupervised feature learning. Proceedings of the Deep Learning and Unsupervised Feature Learning Workshop (NIPS 2011), Granada, Spain.