Affiliation:
1. Information and Navigation School, Air Force Engineering University, Xi’an 710038, China
2. Air Defense and Antimissile School, Air Force Engineering University, Xi’an 710038, China
Abstract
With the advent of deep learning and the accessibility of massive data, scene classification algorithms based on deep learning have been extensively researched and have achieved exciting developments. However, the success of deep models often relies on a large amount of annotated remote sensing data. Additionally, deep models are typically trained and tested on the same set of classes, leading to compromised generalization performance when encountering new classes. This is where few-shot learning aims to enable models to quickly generalize to new classes with only a few reference samples. In this paper, we propose a novel collaborative self-supervised transductive few-shot learning (CS2TFSL) algorithm for remote sensing scene classification. In our approach, we construct two distinct self-supervised auxiliary tasks to jointly train the feature extractor, aiming to obtain a powerful representation. Subsequently, the feature extractor’s parameters are frozen, requiring no further training, and transferred to the inference stage. During testing, we employ transductive inference to enhance the associative information between the support and query sets by leveraging additional sample information in the data. Extensive comparisons with state-of-the-art few-shot scene classification algorithms on the WHU-RS19 and NWPU-RESISC45 datasets demonstrate the effectiveness of the proposed CS2TFSL. More specifically, CS2TFSL ranks first in the settings of five-way one-shot and five-way five-shot. Additionally, detailed ablation experiments are conducted to analyze the CS2TFSL. The experimental results reveal significant and promising performance improvements in few-shot scene classification through the combination of self-supervised learning and direct transductive inference.
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference60 articles.
1. Remote sensing image scene classification meets deep learning: Challenges, methods, benchmarks, and opportunities;Cheng;IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.,2020
2. Zhu, Q., Guo, X., Li, Z., and Li, D. (2022). A review of multi-class change detection for satellite remote sensing imagery. Geo-Spat. Inf. Sci., 1–15.
3. Wang, Z., Li, J., Liu, Y., Xie, F., and Li, P. (2022). An adaptive surrogate-assisted endmember extraction framework based on intelligent optimization algorithms for hyperspectral remote sensing images. Remote Sens., 14.
4. Cost-sensitive self-paced learning with adaptive regularization for classification of image time series;Li;IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.,2021
5. Land-use/land-cover change detection based on a Siamese global learning framework for high spatial resolution remote sensing imagery;Zhu;ISPRS J. Photogramm. Remote Sens.,2022
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献