基于自编码器的零样本学习方法研究进展

Research Progress of Zero-Shot Learning Method Based on AutoEncoder

零样本学习不需要额外的样本标注以及训练数据,便能有效地扩展模型识别能力,这个特点使之成为一个热门而实用的研究领域。近年来,基于自编码器的零样本学习方法不仅能有效解决映射域偏移问题,更是在分类、识别等任务上带来精度的显著提升,这引起学者们的广泛关注。通过对自编码器应用到零样本学习上的方式进行分析归纳,为基于自编码器的零样本学习方法的进一步研究提供理论基础。

Zero-Shot Learning can effectively expand the model recognition ability without additional sample annotation and training data,which makes it a hot and practical research field.In recent years,the Zero-Shot Learning method based on AutoEncoder can not only effectively solve the problem of projection domain shift,but also bring significant improvement in the accuracy of classification,recognition and other tasks,which has attracted extensive attention of scholars.Analyzes and sums up the ways of AutoEncoder applied to Zero-Shot Learning,which provides a theoretical basis for further research on Zero-Shot Learning method based on AutoEncoder.