计算机科学
领域(数学分析)
光学(聚焦)
人工智能
学习迁移
微调
标记数据
人工神经网络
机器学习
模式识别(心理学)
数学
物理
数学分析
量子力学
光学
作者
Jaehoon Oh,Sungnyun Kim,Namgyu Ho,Jin-Hwa Kim,Hwanjun Song,Se-Young Yun
标识
DOI:10.1145/3511808.3557681
摘要
Cross-domain few-shot learning (CD-FSL), where there are few target samples under extreme differences between source and target domains, has recently attracted huge attention. Recent studies on CD-FSL generally focus on transfer learning based approaches, where a neural network is pre-trained on popular labeled source domain datasets and then transferred to target domain data. Although the labeled datasets may provide suitable initial parameters for the target data, the domain difference between the source and target might hinder fine-tuning on the target domain. This paper proposes a simple yet powerful method that re-randomizes the parameters fitted on the source domain before adapting to the target data. The re-randomization resets source-specific parameters of the source pre-trained model and thus facilitates fine-tuning on the target domain, improving few-shot performance.
科研通智能强力驱动
Strongly Powered by AbleSci AI