Version 1
: Received: 1 October 2020 / Approved: 2 October 2020 / Online: 2 October 2020 (09:24:19 CEST)
Version 2
: Received: 14 December 2020 / Approved: 15 December 2020 / Online: 15 December 2020 (13:21:49 CET)
Zhang, P.; Bai, Y.; Wang, D.; Bai, B.; Li, Y. Few-Shot Classification of Aerial Scene Images via Meta-Learning. Remote Sensing, 2020, 13, 108. https://doi.org/10.3390/rs13010108.
Zhang, P.; Bai, Y.; Wang, D.; Bai, B.; Li, Y. Few-Shot Classification of Aerial Scene Images via Meta-Learning. Remote Sensing, 2020, 13, 108. https://doi.org/10.3390/rs13010108.
Cite as:
Zhang, P.; Bai, Y.; Wang, D.; Bai, B.; Li, Y. Few-Shot Classification of Aerial Scene Images via Meta-Learning. Remote Sensing, 2020, 13, 108. https://doi.org/10.3390/rs13010108.
Zhang, P.; Bai, Y.; Wang, D.; Bai, B.; Li, Y. Few-Shot Classification of Aerial Scene Images via Meta-Learning. Remote Sensing, 2020, 13, 108. https://doi.org/10.3390/rs13010108.
Abstract
CNN-based methods have dominated the field of aerial scene classification for the past few years. While achieving remarkable success, CNN-based methods suffer from excessive parameters and notoriously rely on large amounts of training data. In this work, we introduce few-shot learning to the aerial scene classification problem. Few-shot learning aims to learn a model on base-set that can quickly adapt to unseen categories in novel-set, using only a few labeled samples. To this end, we proposed a meta-learning method for few-shot classification of aerial scene images. First, we train a feature extractor on all base categories to learn a representation of inputs. Then in the meta-training stage, the classifier is optimized in the metric space by cosine distance with a learnable scale parameter. At last, in the meta-testing stage, the query sample in the unseen category is predicted by the adapted classifier given a few support samples. We conduct extensive experiments on two challenging datasets: NWPU-RESISC45 and RSD46-WHU. The experimental results show that our method yields state-of-the-art performance. Furthermore, several ablation experiments are conducted to investigate the effects of dataset scale, the impact of different metrics and the number of support shots; the experiment results confirm that our model is specifically effective in few-shot settings.
Keywords
aerial scene classification; remote-sensing image classification; few-shot learning; meta-learning
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Received:
15 December 2020
Commenter:
Ying Li
Commenter's Conflict of Interests:
Author
Comment:
We re-implement three methods (i.e., MAML, ProtoNet, RelationNet) with ResNet-12 backbone for a fair comparison. Besides that, we have added three recent methods for comparison, including TADAM (NIPS2018), MetaOpt(CVPR2019), DSN-MR(CVPR2020). Finally, we added an ablation study of the effect of metrics. This version was resubmitted to remote sensing on 2020-11-16.
Commenter: Ying Li
Commenter's Conflict of Interests: Author
effect of metrics.
This version was resubmitted to remote sensing on 2020-11-16.