SEEN: Few-Shot Classification with SElf-ENsemble

Jiang，Weisen1,2; Zhang，Yu1; Kwok，James T.2

10.1109/IJCNN52387.2021.9533845

2021-07-18

International Joint Conference on Neural Networks (IJCNN)

2161-4393

978-1-6654-4597-9

Proceedings of the International Joint Conference on Neural Networks

2021-July

1-8

JUL 18-22, 2021

null,null,ELECTR NETWORK

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

Few-shot classification aims at learning new concepts with only a few labeled examples. In this paper, we focus on metric-based methods that have achieved state-of-the-art performance. However, they classify query examples based on embeddings extracted from only the last layer. These embeddings tend to be class-specific and may not generalize well to novel classes or domains. To alleviate this problem, we propose the SElf-ENsemble (SEEN) that leverages embeddings from multiple layers. Specifically, a base classifier is built for each of the last few layers, and the resultant base classifiers are then combined together. Experiments on various benchmark datasets demonstrate that the proposed SEEN method outperforms existing methods in both standard few-shot classification and cross-domain few-shot classification scenarios.

few-shot learning meta-learning

第一 ; 通讯

英语

CPCI-S ; EI

NSFC[62076118]

Computer Science ; Engineering

Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Engineering, Electrical & Electronic

WOS:000722581704051

20214110996154

Classification (of information) ; Computer vision

Information Theory and Signal Processing:716.1 ; Artificial Intelligence:723.4 ; Computer Applications:723.5 ; Vision:741.2 ; Information Sources and Analysis:903.1

2-s2.0-85116490539

Scopus

1.Southern University of Science and Technology,Department of Computer Science and Engineering,China
2.Hong Kong University of Science and Technology,Department of Computer Science and Engineering,Hong Kong

Jiang，Weisen,Zhang，Yu,Kwok，James T.. SEEN: Few-Shot Classification with SElf-ENsemble[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2021:1-8.