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
  • [31] Cross-domain few-shot learning based on feature adaptive distillation
    Dingwei Zhang
    Hui Yan
    Yadang Chen
    Dichao Li
    Chuanyan Hao
    Neural Computing and Applications, 2024, 36 : 4451 - 4465
  • [32] Cross-domain Few-shot Learning with Task-specific Adapters
    Li, Wei-Hong
    Liu, Xialei
    Bilen, Hakan
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 7151 - 7160
  • [33] Task context transformer and GCN for few-shot learning of cross-domain
    Li, Pengfang
    Liu, Fang
    Jiao, Licheng
    Li, Lingling
    Chen, Puhua
    Li, Shuo
    NEUROCOMPUTING, 2023, 548
  • [34] CDFSL-V: Cross-Domain Few-Shot Learning for Videos
    Samarasinghe, Sarinda
    Rizve, Mamshad Nayeem
    Kardan, Navid
    Shah, Mubarak
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 11609 - 11618
  • [35] Target Oriented Dynamic Adaption for Cross-Domain Few-Shot Learning
    Chang, Xinyi
    Du, Chunyu
    Song, Xinjing
    Liu, Weifeng
    Wang, Yanjiang
    NEURAL PROCESSING LETTERS, 2024, 56 (03)
  • [36] Task-aware Adaptive Learning for Cross-domain Few-shot Learning
    Guo, Yurong
    Du, Ruoyi
    Dong, Yuan
    Hospedales, Timothy
    Song, Yi-Zhe
    Ma, Zhanyu
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV, 2023, : 1590 - 1599
  • [37] Cross-domain few-shot learning based on feature adaptive distillation
    Zhang, Dingwei
    Yan, Hui
    Chen, Yadang
    Li, Dichao
    Hao, Chuanyan
    NEURAL COMPUTING & APPLICATIONS, 2024, 36 (08): : 4451 - 4465
  • [38] Deep Cross-Domain Few-Shot Learning for Hyperspectral Image Classification
    Li, Zhaokui
    Liu, Ming
    Chen, Yushi
    Xu, Yimin
    Li, Wei
    Du, Qian
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [39] Adaptive Parametric Prototype Learning for Cross-Domain Few-Shot Classification
    Heidari, Marzi
    Alchihabi, Abdullah
    En, Qing
    Guo, Yuhong
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 238, 2024, 238
  • [40] Hyperbolic Insights With Knowledge Distillation for Cross-Domain Few-Shot Learning
    Yang, Xi
    Kong, Dechen
    Wang, Nannan
    Gao, Xinbo
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2025, 34 : 1921 - 1933