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
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
  • [1] A fine-tuning prototypical network for few-shot cross-domain fault diagnosis
    Zhong, Jianhua
    Gu, Kairong
    Jiang, Haifeng
    Liang, Wei
    Zhong, Shuncong
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2024, 35 (11)
  • [2] Toward Better Generalization of Cross-Domain Few-Shot Classification in Tibetan Character With Contrastive Learning and Meta Fine-Tuning
    Bao, Xun
    Wang, Weilan
    Wang, Xiaojuan
    Zhao, Guanzhong
    Li, Huarui
    Liu, Meiling
    IEEE ACCESS, 2024, 12 : 134439 - 134452
  • [3] Adaptive fine-tuning strategy for few-shot learning
    Zhuang, Xinkai
    Shao, Mingwen
    Gao, Wei
    Yang, Jianxin
    JOURNAL OF ELECTRONIC IMAGING, 2022, 31 (06)
  • [4] Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty
    Oh, Jaehoon
    Kim, Sungnyun
    Ho, Namgyu
    Kim, Jin-Hwa
    Song, Hwanjun
    Yun, Se-Young
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [5] Knowledge transduction for cross-domain few-shot learning
    Li, Pengfang
    Liu, Fang
    Jiao, Licheng
    Li, Shuo
    Li, Lingling
    Liu, Xu
    Huang, Xinyan
    PATTERN RECOGNITION, 2023, 141
  • [6] Bayesian Sharpness-Aware Prompt Tuning for Cross-Domain Few-shot Learning
    Fan, Shuo
    Zhuang, Liansheng
    Li, Aodi
    2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
  • [7] Feature extractor stacking for cross-domain few-shot learning
    Wang, Hongyu
    Frank, Eibe
    Pfahringer, Bernhard
    Mayo, Michael
    Holmes, Geoffrey
    MACHINE LEARNING, 2024, 113 (01) : 121 - 158
  • [8] Ranking Distance Calibration for Cross-Domain Few-Shot Learning
    Li, Pan
    Gong, Shaogang
    Wang, Chengjie
    Fu, Yanwei
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2022, : 9089 - 9098
  • [9] Spectral Decomposition and Transformation for Cross-domain Few-shot Learning
    Liu, Yicong
    Zou, Yixiong
    Li, Ruixuan
    Li, Yuhua
    NEURAL NETWORKS, 2024, 179
  • [10] Experiments in cross-domain few-shot learning for image classification
    Wang, Hongyu
    Gouk, Henry
    Fraser, Huon
    Frank, Eibe
    Pfahringer, Bernhard
    Mayo, Michael
    Holmes, Geoffrey
    JOURNAL OF THE ROYAL SOCIETY OF NEW ZEALAND, 2023, 53 (01) : 169 - 191