Knowledge Commons of Institute of Automation,CAS
Prototype Calibration with Synthesized Samples for Zero-Shot Chinese Character Recognition | |
Ao, Xiang1![]() ![]() ![]() ![]() | |
2024-04 | |
会议名称 | 2024 IEEE International Conference on Acoustics, Speech and Signal Processing |
会议日期 | 14-19 April 2024 |
会议地点 | Seoul, Korea |
摘要 | Zero-shot Chinese character recognition aims to recognize unseen characters that have never appeared in training. Recently, many methods learn a cross-modal alignment between character samples and auxiliary semantic data like glyph templates in training, and directly employ it to recognize unseen characters by retrieving the class with most similar semantics. However, these approaches suffer from the domain shift problem, which means that the learned alignment shows a deviation on unseen characters. To alleviate this problem, we generate unseen character samples to calibrate the shifted prototypes in the feature space. Specifically, we train a cross-modal prototype classifier and a generator conditioned on glyph templates, then use the generator to synthesize unseen character samples to calibrate the prototypes of the classifier. The calibration process does not require any extra training. Experiments on a handwritten dataset and a nature scene dataset show the superiority of our method and the effectiveness of prototype calibration. |
收录类别 | EI |
七大方向——子方向分类 | 文字识别与文档分析 |
国重实验室规划方向分类 | 小样本高噪声数据学习 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/56732 |
专题 | 多模态人工智能系统全国重点实验室_模式分析与学习 |
通讯作者 | Liu, Cheng-Lin |
作者单位 | 1.MAIS, Institute of Automation of Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Ao, Xiang,Li, Xiao-Hui,Zhang, Xu-Yao,et al. Prototype Calibration with Synthesized Samples for Zero-Shot Chinese Character Recognition[C],2024. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Prototype_Calibratio(1434KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论