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
  • [21] RIFF: Learning to Rephrase Inputs for Few-shot Fine-tuning of Language Models
    Najafi, Saeed
    Fyshe, Alona
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: ACL 2024, 2024, : 1447 - 1466
  • [22] HybridPrompt: Domain-Aware Prompting for Cross-Domain Few-Shot Learning
    Wu, Jiamin
    Zhang, Tianzhu
    Zhang, Yongdong
    International Journal of Computer Vision, 132 (12): : 5681 - 5697
  • [23] Fine-Tuning of CLIP in Few-Shot Scenarios via Supervised Contrastive Learning
    Luo, Jing
    Wu, Guangxing
    Liu, Hongmei
    Wang, Ruixuan
    PATTERN RECOGNITION AND COMPUTER VISION, PT III, PRCV 2024, 2025, 15033 : 104 - 117
  • [24] Cross-domain few-shot learning via adaptive transformer networks
    Paeedeh, Naeem
    Pratama, Mahardhika
    Ma'sum, Muhammad Anwar
    Mayer, Wolfgang
    Cao, Zehong
    Kowlczyk, Ryszard
    KNOWLEDGE-BASED SYSTEMS, 2024, 288
  • [25] Cross-Domain Few-Shot Contrastive Learning for Hyperspectral Images Classification
    Zhang, Suhua
    Chen, Zhikui
    Wang, Dan
    Wang, Z. Jane
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [26] Dual Adaptive Representation Alignment for Cross-Domain Few-Shot Learning
    Zhao Y.
    Zhang T.
    Li J.
    Tian Y.
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45 (10) : 11720 - 11732
  • [27] A Divide-and-Conquer Strategy for Cross-Domain Few-Shot Learning
    Wang, Bingxin
    Yu, Dehong
    ELECTRONICS, 2025, 14 (03):
  • [28] CDCNet: Cross-domain few-shot learning with adaptive representation enhancement
    Li, Xueying
    He, Zihang
    Zhang, Lingyan
    Guo, Shaojun
    Hu, Bin
    Guo, Kehua
    PATTERN RECOGNITION, 2025, 162
  • [29] Learning general features to bridge the cross-domain gaps in few-shot
    Li, Xiang
    Luo, Hui
    Zhou, Gaofan
    Peng, Xiaoming
    Wang, Zhixing
    Zhang, Jianlin
    Liu, Dongxu
    Li, Meihui
    Liu, Yungfeng
    KNOWLEDGE-BASED SYSTEMS, 2024, 299
  • [30] Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognition
    Hatano, Masashi
    Hachiuma, Ryo
    Fujii, Ryo
    Saito, Hideo
    COMPUTER VISION - ECCV 2024, PT XXXIII, 2025, 15091 : 182 - 199