Abstract | ||
---|---|---|
Few-Shot Learning (FSL) aims at recognizing the target classes that only a few samples are available for training. The current approaches mostly address FSL by learning a generalized class-level metric while neglect the intra-class distribution information. In this work, we propose Improved Prototypical Networks (IPN) to address this issue. Inspired by the observation that the intra-class samples differ greatly in revealing the class distribution, we first propose an attention-analogous strategy to explore the class distribution information by distributing different weights to samples based on their representativeness. Besides, to further explore the discriminative information across classes, we propose a distance scaling strategy to reduce the intra-class difference while enlarge the inter-class difference. The experimental results on two benchmark datasets show the superiority of the proposed model against the state-of-the-art approaches. (C) 2020 Elsevier B.V. All rights reserved. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.patrec.2020.07.015 | PATTERN RECOGNITION LETTERS |
Keywords | DocType | Volume |
Image classification, Attention network, Few-Shot learning, Metric learning | Journal | 140 |
ISSN | Citations | PageRank |
0167-8655 | 1 | 0.35 |
References | Authors | |
24 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhong Ji | 1 | 93 | 8.95 |
Xingliang Chai | 2 | 3 | 0.73 |
Yunlong Yu | 3 | 31 | 3.23 |
Yanwei Pang | 4 | 192 | 14.61 |
Zhongfei (Mark) Zhang | 5 | 2451 | 164.30 |