arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.08288cs.CV
收藏

基于变换的降维

Transformer-based dimensionality reduction

Chongqing Normal University(重庆师范大学);Chongqing University(重庆大学)

Ruisheng Ran, Tianyu Gao, Bin Fang

摘要:

近年来,Transformer在机器学习(ML)、自然语言处理(NLP)、计算机视觉(CV)等领域发挥着重要作用。本文在视觉Transformer(ViT)模型的基础上,提出了一种新的降维(DR)模型--Transformer-DR。从数据可视化、图像重建和人脸识别三个方面,研究了降维后的Transformer-DR的表示能力,并与一些有代表性的DR方法进行了比较,以了解Transformer-DR与现有DR方法的区别。实验结果表明,Transformer-DR是一种有效的降维方法。

英文摘要:

Recently, Transformer is much popular and plays an important role in the fields of Machine Learning (ML), Natural Language Processing (NLP), and Computer Vision (CV), etc. In this paper, based on the Vision Transformer (ViT) model, a new dimensionality reduction (DR) model is proposed, named Transformer-DR. From data visualization, image reconstruction and face recognition, the representation ability of Transformer-DR after dimensionality reduction is studied, and it is compared with some representative DR methods to understand the difference between Transformer-DR and existing DR methods. The experimental results show that Transformer-DR is an effective dimensionality reduction method.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑