Towards better long-tailed oracle character recognition with adversarial data augmentation. (August 2023)

• Record Type: Journal Article
• Authors: Li, Jing; Wang, Qiu-Feng; Huang, Kaizhu; Yang, Xi; Zhang, Rui; Goulermas, John Y.
• Is Part Of: Pattern recognition. Volume 140(2023)
• Publication Date: 2023-08
• Subjects: Oracle character recognition -- Long tail -- Data imbalance -- Data augmentation -- Mixup strategy -- Generative adversarial networks; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2023.109534
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: To our knowledge, it is the first work to study intensively mixup methods within the GAN framework for adversarial data augmentation in the long-tailed oracle character recognition. We propose two novel mixup-based methods, including Repatch to generalize samples in the mixup generator and the TailMix mechanism to replenish samples in the tail classes for the adversarial generator. We extensively validate the proposed model on three benchmark oracle datasets (Oracle-AYNU, OBC306 and Oracle-20K). Experimental results show that our model can yield the state-of-the-art performance as opposed to other existing oracle recognition methods. Abstract: Deciphering oracle bone script is of great significance to the study of ancient Chinese culture as well as archaeology. Although recent studies on oracle character recognition have made substantial progress, they still suffer from the long-tailed data situation that results in a noticeable performance drop on the tail classes. To mitigate this issue, we propose a generative adversarial framework to augment oracle characters in the problematic classes. In this framework, the generator produces synthetic data through convex combinations of all the available samples in the corresponding classes, and is further optimized through adversarial learning with the classifier and simultaneously the discriminator. Meanwhile, we introduce Repatch to generalize samples in the generator. Since tail classes do not have sufficient data for convex combinations, we propose the TailMix mechanism to generate suitable tail class samples from other classes. Experimental results show that our proposed algorithm obtains remarkable performance in oracle character recognition and achieves new state-of-the-art average (total) accuracy with 86.03% (89.46%), 86.54% (93.86%), 95.22% (96.17%) on the three datasets Oracle-AYNU, OBC306 and Oracle-20K, respectively.