Due to low frequency of occurrence of some characters in Oracle,directly using the deep neural network for recognition will produce serious overfitting,which will lead to poor recognition accuracy.To this end,this paper pro-poses a few-shot oracle bone character recognition method based on supervised contrastive learning.The ensemble aug-mented-shot Y-shaped(EASY)learning framework is selected as the backbone part of the network.Through training techniques such as collective data enhancement,multi-backbone network integration,and feature vector projection,etc.,it is possible to directly use a small number of labeled samples for identification.And then,introducing the supervised contrastive learning and the concept of a joint contrastive loss to make the intra-class feature vectors in the feature space closer and the inter-class feature vectors further apart,thereby the model performance is improved further.The experi-mental results show that compared with the current best-performing Orc-Bert model,the accuracy of the few-shot or-acle recognition model proposed in this paper has increased by 26.42%in the 1-shot task,28.55%in the 3-shot task,and 23.98%in the 5-shot task,which better solves the problem of poor recognition accuracy of low-frequency oracle bone characters.
关键词
甲骨文字识别/小样本/监督对比学习/利用增强样本的Y型学习框架/深度学习/特征空间/联合对比损失
Key words
oracle bone character recognition/few-shot/supervised contrastive learning/EASY framework/deep learn-ing/feature space/joint contrastive loss
维普
万方数据