Complementary features based prototype self-updating for few-shot learning. (15th March 2023)

• Record Type: Journal Article
• Authors: Xu, Xinlei; Wang, Zhe; Chi, Ziqiu; Yang, Hai; Du, Wenli
• Is Part Of: Expert systems with applications. Volume 214(2023)
• Publication Date: 2023-03-15
• Subjects: Few-shot learning -- Prototype learning -- Complementary features; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2022.119067
• Languages: English
• ISSNs: 0957-4174

Abstract

Abstract: The goal of few-shot learning is to use limited labeled samples to complete independent classification tasks. The feature extractor of few-shot learning needs to have a stronger feature expression ability to generalize in unseen novel classes. To further enhance the expressive ability, in this paper, we propose an inherited feature extraction method, named Base and Meta Feature Extraction (BMFE). Base feature represents the task-irrelevant classification information of each sample. Meta feature obtained by the proposed Triplet Meta-train Mechanism (TMM) inherits the classification information and also contains the task-related meta information of each sample. We concatenate both the base and meta features to complementarily express the rich information of each sample. Besides, instead of relying on limited support samples to obtain the prototype, we propose a novel unsupervised prototype correction module, named Prototype Self-updating (PSU). All unlabeled query samples in a few-shot test task participate in the iterative updating of each prototype in the task without training. Extensive experiments prove that our overall method can obtain richer features by BMFE and more accurate prototypes by PSU. Our overall method outperforms state-of-the-art methods on miniImageNet and tiredImageNet datasets, and especially under the 1-shot case we obtains 78.45% and 81.21% classification accuracy respectively. Highlights: BMFE can obtain the complementary features representation of FSL. TMM mechanism can better perform meta-training of BMFE. PSU can correct prototypes without training process. The proposed CFPSU gets outstanding results on two standard datasets.