Paper Info
Title
Rethinking the Metric in Few-shot Learning: From an Adaptive Multi-Distance Perspective
Abstract
ABSTRACTFew-shot learning problem focuses on recognizing unseen classes given a few labeled images. In recent effort, more attention is paid to fine-grained feature embedding, ignoring the relationship among different distance metrics. In this paper, for the first time, we investigate the contributions of different distance metrics, and propose an adaptive fusion scheme, bringing significant improvements in few-shot classification. We start from a naive baseline of confidence summation and demonstrate the necessity of exploiting the complementary property of different distance metrics. By finding the competition problem among them, built upon the baseline, we propose an Adaptive Metrics Module (AMM) to decouple metrics fusion into metric-prediction fusion and metric-losses fusion. The former encourages mutual complementary, while the latter alleviates metric competition via multi-task collaborative learning. Based on AMM, we design a few-shot classification framework AMTNet, including the AMM and the Global Adaptive Loss (GAL), to jointly optimize the few-shot task and auxiliary self-supervised task, making the embedding features more robust. In the experiment, the proposed AMM achieves 2% higher performance than the naive metrics fusion module, and our AMTNet outperforms the state-of-the-arts on multiple benchmark datasets.
Year
DOI
Venue
2022
10.1145/3503161.3547853
International Multimedia Conference
DocType
ISSN
Citations 
Conference
Proceedings of the 30th ACM International Conference on Multimedia 2022
0
PageRank 
References 
Authors
0.34
0
12
Name
Order
Citations
PageRank
Jinxiang Lai100.68
Siqian Yang200.68
Guannan Jiang301.01
Xi Wang400.34
Yuxi Li500.34
Zihui Jia600.34
Xiaochen Chen700.34
Jun Liu817825.96
Bin-Bin Gao900.68
Wei Zhang1012.39
Yuan Xie116430407.00
Chengjie Wang124319.03