Hybrid Fine-Tuning Strategy for Few-Shot Classification

doi:10.1155/2022/9620755

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 机器人理论与应用

	Hybrid Fine-Tuning Strategy for Few-Shot Classification
	Zhao, Lei 1,2; Ou, Zhonghua 2; Zhang, Lixun 2; Li, Shuxiao1
发表期刊	COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
ISSN	1687-5265
	2022-10-08
卷号	2022 页码:12
通讯作者	Li, Shuxiao(shuxiao.li@ia.ac.cn)
摘要	Few-shot classification aims to enable the network to acquire the ability of feature extraction and label prediction for the target categories given a few numbers of labeled samples. Current few-shot classification methods focus on the pretraining stage while fine-tuning by experience or not at all. No fine-tuning or insufficient fine-tuning may get low accuracy for the given tasks, while excessive fine-tuning will lead to poor generalization for unseen samples. To solve the above problems, this study proposes a hybrid fine-tuning strategy (HFT), including a few-shot linear discriminant analysis module (FSLDA) and an adaptive fine-tuning module (AFT). FSLDA constructs the optimal linear classification function under the few-shot conditions to initialize the last fully connected layer parameters, which fully excavates the professional knowledge of the given tasks and guarantees the lower bound of the model accuracy. AFT adopts an adaptive fine-tuning termination rule to obtain the optimal training epochs to prevent the model from overfitting. AFT is also built on FSLDA and outputs the final optimum hybrid fine-tuning strategy for a given sample size and layer frozen policy. We conducted extensive experiments on mini-ImageNet and tiered-ImageNet to prove the effectiveness of our proposed method. It achieves consistent performance improvements compared to existing fine-tuning methods under different sample sizes, layer frozen policies, and few-shot classification frameworks.
DOI	10.1155/2022/9620755
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China ; [U19B2033] ; [62076020]
项目资助者	National Natural Science Foundation of China
WOS研究方向	Mathematical & Computational Biology ; Neurosciences & Neurology
WOS类目	Mathematical & Computational Biology ; Neurosciences
WOS记录号	WOS:000884395500001
出版者	HINDAWI LTD
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/51273
专题	多模态人工智能系统全国重点实验室_机器人理论与应用
通讯作者	Li, Shuxiao
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 2.Univ Elect Sci & Technol China, Chengdu, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Zhao, Lei,Ou, Zhonghua,Zhang, Lixun,et al. Hybrid Fine-Tuning Strategy for Few-Shot Classification[J]. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE,2022,2022:12.
APA	Zhao, Lei,Ou, Zhonghua,Zhang, Lixun,&Li, Shuxiao.(2022).Hybrid Fine-Tuning Strategy for Few-Shot Classification.COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE,2022,12.
MLA	Zhao, Lei,et al."Hybrid Fine-Tuning Strategy for Few-Shot Classification".COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2022(2022):12.