University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Meta metric learning for highly imbalanced aerial scene classification

Guan, Jin, Liu, Jiabei, Sun, Jianguo, Feng, Pengming, Shuai, Tong and Wang, Wenwu (2020) Meta metric learning for highly imbalanced aerial scene classification In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2020),, May 4 to 8, 2020, Barcelona, Spain.

GuanLSFSW_ICASSP_2020.pdf - Accepted version Manuscript

Download (1MB) | Preview


Class imbalance is an important factor that affects the performance of deep learning models used for remote sensing scene classification. In this paper, we propose a random finetuning meta metric learning model (RF-MML) to address this problem. Derived from episodic training in meta metric learning, a novel strategy is proposed to train the model, which consists of two phases, i.e., random episodic training and all classes fine-tuning. By introducing randomness into the episodic training and integrating it with fine-tuning for all classes, the few-shot meta-learning paradigm can be successfully applied to class imbalanced data to improve the classification performance. Experiments are conducted to demonstrate the effectiveness of the proposed model on class imbalanced datasets, and the results show the superiority of our model, as compared with other state-of-the-art methods.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
Guan, Jin
Liu, Jiabei
Sun, Jianguo
Feng, Pengming
Shuai, Tong
Date : 24 January 2020
Uncontrolled Keywords : Remote sensing, scene classification, class imbalance, meta-learning, metric learning
Depositing User : James Marshall
Date Deposited : 20 Feb 2020 13:25
Last Modified : 20 Feb 2020 13:25

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800