ROI Regularization for Semi-supervised and Supervised Learning

TL;DR

This paper introduces ROI regularization, a semi-supervised learning technique that enhances CNN classification by focusing on image regions contributing most to predictions, and combines it with VAT for improved accuracy.

Contribution

The paper proposes ROI regularization (ROIreg), a novel semi-supervised method that refines CNN classification by focusing on important image regions, and introduces ROI augmentation for supervised learning.

Findings

ROIreg improves classification accuracy on SVHN and CIFAR-10 datasets.

Combining ROIreg with VAT yields state-of-the-art results.

ROI augmentation enhances supervised learning performance.

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.