ReFine: Re-randomization before Fine-tuning for Cross-domain Few-shot Learning

被引:4
|
作者
Oh, Jaehoon [1 ]
Kim, Sungnyun [2 ]
Ho, Namgyu [2 ]
Kim, Jin-Hwa [3 ]
Song, Hwanjun [3 ]
Yun, Se-Young [2 ]
机构
[1] KAIST DS, Daejeon, South Korea
[2] KAIST AI, Seoul, South Korea
[3] NAVER AI Lab, Sungnam, South Korea
来源
PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, CIKM 2022 | 2022年
关键词
cross-domain; few-shot; transfer learning; re-randomization;
D O I
10.1145/3511808.3557681
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
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.
引用
收藏
页码:4359 / 4363
页数:5
相关论文
共 50 条
  • [41] Metric-Based Meta-Learning for Cross-Domain Few-Shot Identification of Welding Defect
    Xie, Tingli
    Huang, Xufeng
    Choi, Seung-Kyum
    JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN ENGINEERING, 2023, 23 (03)
  • [42] DOMAIN-SPECIFIC AND DOMAIN-COMMON FEATURE ENHANCEMENT FOR CROSS-DOMAIN FEW-SHOT HYPERSPECTRAL IMAGE CLASSIFICATION
    Gao, Wenfei
    Liu, Fang
    Liu, Jia
    Xiao, Liang
    Tang, Xu
    IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2023, : 7661 - 7664
  • [43] Improved metric-based meta learning with attention mechanism for few-shot cross-domain train bearing fault diagnosis
    Zhong, Hao
    He, Deqiang
    Lao, Zhenpeng
    Jin, Zhenzhen
    Shen, Guoqiang
    Chen, Yanjun
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2024, 35 (07)
  • [44] Domain adaptation meta-learning network with discard-supplement module for few-shot cross-domain rotating machinery fault diagnosis
    Zhang, Yu
    Han, Dongying
    Tian, Jinghui
    Shi, Peiming
    KNOWLEDGE-BASED SYSTEMS, 2023, 268
  • [45] Cross-Domain Few-Shot Hyperspectral Image Classification With Class-Wise Attention
    Wang, Wenzhen
    Liu, Fang
    Liu, Jia
    Xiao, Liang
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
  • [46] Global-local prototype-based few-shot learning for cross-domain hyperspectral image classification
    Tang, Haojin
    Wu, Yuelin
    Li, Hongyi
    Tang, Dong
    Yang, Xiaofei
    Xie, Weixin
    KNOWLEDGE-BASED SYSTEMS, 2025, 314
  • [47] SELM: Self-Motivated Ensemble Learning Model for Cross-Domain Few-Shot Classification in Hyperspectral Images
    Zhao, Shiyuan
    Bai, Yu
    Shao, Shuai
    Liu, Weifeng
    Ge, Xinmin
    Li, Ye
    Liu, Baodi
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2024, 21 : 1 - 5
  • [48] Topological Information Aggregation Network for Few-Shot Cross-Domain Hyperspectral Image Classification
    Shi, Kai
    Wang, Wenzhen
    Liu, Qichao
    Xiao, Liang
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2025, 63
  • [49] CATFSID: A few-shot human identification system based on cross-domain adversarial training
    Wei, Zhongcheng
    Chen, Wei
    Tao, Weitao
    Ning, Shuli
    Lian, Bin
    Sun, Xiang
    Zhao, Jijun
    COMPUTER COMMUNICATIONS, 2024, 224 : 275 - 284
  • [50] An efficient cross-domain few-shot website fingerprinting attack with Brownian distance covariance
    Zou, Hongcheng
    Su, Jinshu
    Wei, Ziling
    Chen, Shuhui
    Zhao, Baokang
    COMPUTER NETWORKS, 2022, 219