ROI Regularization for Semi-supervised and Supervised Learning
arXiv:1905.08615
Abstract
We propose ROI regularization (ROIreg) as a semi-supervised learning method for image classification. ROIreg focuses on the maximum probability of a posterior probability distribution g(x) obtained when inputting an unlabeled data sample x into a convolutional neural network (CNN). ROIreg divides the pixel set of x into multiple blocks and evaluates, for each block, its contribution to the maximum probability. A masked data sample x_ROI is generated by replacing blocks with relatively small degrees of contribution with random images. Then, ROIreg trains CNN so that g(x_ROI ) does not change as much as possible from g(x). Therefore, ROIreg can be said to refine the classification ability of CNN more. On the other hand, Virtual Adverserial Training (VAT), which is an excellent semi-supervised learning method, generates data sample x_VAT by perturbing x in the direction in which g(x) changes most. Then, VAT trains CNN so that g(x_VAT ) does not change from g(x) as much as possible. Therefore, VAT can be said to be a method to improve CNN's weakness. Thus, ROIreg and VAT have complementary training effects. In fact, the combination of VAT and ROIreg improves the results obtained when using VAT or ROIreg alone. This combination also improves the state-of-the-art on "SVHN with and without data augmentation" and "CIFAR-10 without data augmentation". We also propose a method called ROI augmentation (ROIaug) as a method to apply ROIreg to data augmentation in supervised learning. However, the evaluation function used there is different from the standard cross-entropy. ROIaug improves the performance of supervised learning for both SVHN and CIFAR-10. Finally, we investigate the performance degradation of VAT and VAT+ROIreg when data samples not belonging to classification classes are included in unlabeled data.
14 pages, 7 tables, 2 figures
References in corpus (10)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Improved Regularization of Convolutional Neural Networks with Cutout
- Improved Techniques for Training GANs
- Random Erasing Data Augmentation
- Semi-Supervised Learning with Ladder Networks
- Good Semi-supervised Learning that Requires a Bad GAN
- Averaging Weights Leads to Wider Optima and Better Generalization
- Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
- There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average
- Colorization as a Proxy Task for Visual Understanding