计算机科学
鉴别器
人工智能
对抗制
领域(数学分析)
机器学习
域适应
特征(语言学)
深度学习
渲染(计算机图形)
特征学习
水准点(测量)
模式识别(心理学)
分类器(UML)
数学
数学分析
电信
语言学
哲学
大地测量学
探测器
地理
作者
Chiori Azuma,Tomoyoshi Ito,Tomoyoshi Shimobaba
标识
DOI:10.1016/j.engappai.2023.106394
摘要
In recent research, problems with biased datasets or domain shift have presented challenges to the practical applications of deep learning methods. In this paper, we propose a simple method using adversarial learning combined with contrastive learning and domain adaptation to solve the domain-shift problem. Because domain shift is caused by differences in the distribution of data across domains, different approaches have been proposed to resolve this by rendering the data distributions closer through adversarial training. Contrastive learning is a method of acquiring valid feature representations for downstream tasks. By combining these approaches, we aim to achieve better domain adaptation. The proposed method is simple and intuitive. By introducing a domain discriminator into SimCLR, which is a typical contrastive learning model, and training it in an adversarial manner, the feature vectors of the source and target domains are rendered closer to acquire domain-invariant features. The proposed approach facilitates high-performance pretraining without labels and demonstrates a significant improvement in accuracy in comparison to standard benchmark methods, including conventional supervised models and SimCLR.
科研通智能强力驱动
Strongly Powered by AbleSci AI