A Framework for Enhanced Adaptability and Interpretability in Meta-Learning
Author:
Affiliation:

1.Guangxi Key Laboratory of Trusted Software, Guilin University of Electronic Technology;2.Guangxi Key Laboratory of Image and Graphic intelligent processing, Guilin University of Electronic Technology;3.School of Information Engineering, Institute of Disaster Prevention

Fund Project:

The Key R&D Program of Guangxi under Grant(AB21220023) ;The National Natural Science Foundation of China (42164002); Guangxi Graduate Education Innovation Project(YCSW2023308)

  • Article
  • | |
  • Metrics
  • |
  • Reference [36]
  • | |
  • Cited by
  • | |
  • Comments
    Abstract:

    In few-shot learning scenarios, Model-Agnostic Meta-Learning (MAML) is renowned for its flexibility and applicability independent of specific base model. However, MAML and its variants lack the ability to adaptively adjust task-specific features, such as feature channels, and rely on global initial parameters with fixed inner-loop step numbers, resulting in a training process that lacks interpretability. This paper proposes a rapid, interpretable, and adaptive method using logistic regression and channel attention (ML-LRCA). The goal is to enhance the adaptability and interpretability of the framework by adaptively adjusting task-specific channel weights and utilizing logistic regression to swiftly adapt to task-specific adaptive loss functions. By conducting experiments on multiple open-source datasets for few-shot classification, cross-domain few-shot classification, and few-shot regression, the results indicate that the proposed ML-LRCA method achieves significant performance improvement.

    Reference
    [1] VILALTA R, DRISSI Y. A perspective view and survey of meta-learning[J]. Artificial intelligence review, 2002, 18: 77-95.
    [2] FINN C, ABBEEL P, LEVINE S. Model-agnostic meta-learning for fast adaptation of deep networks[C]//International conference on machine learning. 2017: 1126-1135.
    [3] ANTONIOU A, EDWARDS H, STORKEY A. How to train your MAML[J]. arXiv preprint arXiv:1810.09502, 2018.
    [4] BERNACCHIA A. Meta-learning with negative learning rates[J]. arXiv preprint arXiv:2102.00940, 2021
    [5] BOHDAL O, YANG Y, HOSPEDALES T. Evograd: Efficient gradient-based meta-learning and hyperparameter optimization[J]. Advances in Neural Information Processing Systems, 2021, 34: 22234-22246.
    [6] LI Z, ZHOU F, CHEN F, et al. Meta-sgd: Learning to learn quickly for few-shot learning[J]. arXiv preprint arXiv:1707.09835, 2017.
    [7] RUSU A A, RAO D, SYGNOWSKI J, et al. Meta-learning with latent embedding optimization[J]. arXiv preprint arXiv:1807.05960, 2018.
    [8] STARSHAK T. Negative Inner-Loop Learning Rates Learn Universal Features[J]. arXiv preprint arXiv:2203.10185, 2022.
    [9] ZOU Y, LIU F, LI Q. Unraveling model-agnostic meta-learning via the adaptation learning rate[C]//International Conference on Learning Representations. 2021.
    [10] WANG M, GONG Q, CHEN H, et al. Optimizing deep transfer networks with fruit fly optimization for accurate diagnosis of diabetic retinopathy[J]. Applied Soft Computing, 2023, 147: 110782.
    [11] BEHL H S, BAYDIN A G, TORR P H. Alpha maml: Adaptive model-agnostic meta-learning[J]. arXiv preprint arXiv:1905.07435, 2019.
    [12] LEE Y, CHOI S. Gradient-based meta-learning with learned layerwise metric and subspace[C]//International Conference on Machine Learning. 2018: 2927-2936.
    [13] BAIK S, CHOI M, CHOI J, et al. Meta-learning with adaptive hyperparameters[J]. Advances in neural information processing systems, 2020, 33: 20755-20765.
    [14] WANG M, GONG Q, WAN Q, et al. A Fast Interpretable Adaptive meta-learning Enhanced Deep Learning Framework for Diagnosis of Diabetic Retinopathy[J]. Expert Systems with Applications, 2023: 123074.
    [15] FUKUI H, HIRAKAWA T, YAMASHITA T, et al. Attention branch network: Learning of attention mechanism for visual explanation[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019: 10705-10714.
    [16] BAIK S, CHOI J, KIM H, et al. Meta-learning with task-adaptive loss function for few-shot learning[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2021: 9465-9474.
    [17] JIANG X, HAVAEI M, VARNO F, et al. Learning to learn with conditional class dependencies[C]//international conference on learning representations. 2018.
    [18] PEREZ E, STRUB F, DE VRIES H, et al. Film: Visual reasoning with a general conditioning layer[C]//Proceedings of the AAAI conference on artificial intelligence: vol. 32: 1. 2018
    [19] ORESHKIN B, RODR ?IGUEZ L? ?OPEZ P, LACOSTE A. Tadam: Task dependent adaptive metric for improved few-shot learning[J]. Advances in neural information processing systems, 2018, 31.
    [20] WOO S, PARK J, LEE J Y, et al. Cbam: Convolutional block attention module[C]//Proceedings of the European conference on computer vision (ECCV). 2018: 3-19.
    [21] QIN Z, ZHANG P, WU F, et al. Fcanet: Frequency channel attention networks[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2021: 783-792.
    [22] ZEILER M D, FERGUS R. Visualizing and understanding convolutional networks[C]//Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part I 13. 2014: 818-833.
    [23] RAVI S, LAROCHELLE H. Optimization as a model for few-shot learning[C]//International conference on learning representations. 2016.
    [24] REN M, TRIANTAFILLOU E, RAVI S, et al. Meta-learning for semi-supervised few-shot classification[J]. arXiv preprint arXiv:1803.00676, 2018
    [25] RUSSAKOVSKY O, DENG J, SU H, et al. Imagenet large scale visual recognition challenge[J]. International journal of computer vision, 2015, 115: 211-252
    [26] BAIK S, HONG S, LEE K M. Learning to forget for meta-learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 2379-2387
    [27] LEE K, MAJI S, RAVICHANDRAN A, et al. Meta-learning with differentiable convexoptimization[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019: 10657-10665
    [28] CHEN W Y, LIU Y C, KIRA Z, et al. A closer look at few-shot classification[J]. arXiv preprint arXiv:1904.04232, 2019.
    [29] 李凡长, 刘洋, 吴鹏翔,等. 元学习研究综述[J].计算机学报,2021,44(2):422-446.
    [30] XU K, BA J, KIROS R, et al. Show, attend and tell: Neural image caption generation with visual attention[C]//International conference on machine learning. 2015: 2048-2057
    [31] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132-7141.
    [32] 刘坚,李树林,陈涛.基于优化随机森林模型的滑坡易发性评价[J].武汉大学学报(信息科学版),2018,43(07):1085-1091.
    [33] 王子民,周悦,关挺强,郭欣,胡巍,王茂发.基于改进U2-Net网络的多裂肌MRI图像分割算法[J].南京信息工程大学学报(自然科学版),2024,16(3):364-373
    WANG Zimin, ZHOU Yue, GUAN Tingqiang, GUO Xin, HU Wei, WANG Maofa.Segmentation of multifidus muscle MRI images via improved U2-Net[J]. Journal of Nanjing University of Information Science Technology, 2024,16(3):364-373
    [34] 黄驰涵,沈肖波.基于融合注意力和特征增强的跨模态行人重识别[J].南京信息工程大学学报(自然科学版),2024,16(4):451-460
    HUANG Chihan, SHEN Xiaobo.Cross-modal person re-identification based on fused attention and feature enhancement[J]. Journal of Nanjing University of Information Science Technology, 2024,16(4):451-460
    [35] LENG Z, WANG M, WAN Q, et al. Meta-learning of feature distribution alignment for enhanced feature sharing[J]. Knowledge-Based Systems, 2024, 296: 111875.
    [36] 师伟婕,黄静静,王茂发.基于两种U型网络的钢铁图像缺陷检测方法对比[J].北京信息科技大学学报(自然科学版),2021,36(01):63-68.
    Related
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation
Share
Article Metrics
  • Abstract:25
  • PDF: 0
  • HTML: 0
  • Cited by: 0
History
  • Received:August 15,2024
  • Revised:September 30,2024
  • Adopted:October 08,2024
Article QR Code

Address:No. 219, Ningliu Road, Nanjing, Jiangsu Province

Postcode:210044

Phone:025-58731025