Remote Sensing Image Scene Classification With Self-Supervised Paradigm Under Limited Labeled Samples

By Chao Tao, Ji Qi, Weipeng Lu, Haifeng Li. 2020

112 citations recorded by the source corpus.

With the development of deep learning, supervised learning methods perform well in remote sensing image (RSI) scene classification. However, supervised learning requires a huge number of annotated data for training. When labeled samples are not sufficient, the most common solution is to fine-tune the pretraining models using a large natural image data set (e.g., ImageNet). However, this learning paradigm is not a panacea, especially when the target RSIs (e.g., multispectral and hyperspectral data) have different imaging mechanisms from RGB natural images. To solve this problem, we introduce a new self-supervised learning (SSL) mechanism to obtain the high-performance pretraining model for RSI scene classification from large unlabeled data. Experiments on three commonly used RSI scene classification data sets demonstrated that this new learning paradigm outperforms the traditional dominant ImageNet pretrained model. Moreover, we analyze the impacts of several factors in SSL on RSI scene classification, including the choice of self-supervised signals, the domain difference between the source and target data sets, and the amount of pretraining data. The insights distilled from this work can help to foster the development of SSL in the remote sensing community. Since SSL could learn from unlabeled massive RSIs, which are extremely easy to obtain, it will be a promising way to alleviate dependence on labeled samples and thus efficiently solve many problems, such as global mapping.

Subfields: Atmospheric Science, Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Continual Barlow Twins: Continual Self-Supervised Learning for Remote Sensing Semantic Segmentation (2022, background): “Other contrastive strategies are proposed by [16] and [17].”
Self-Supervised Pretraining Improves Self-Supervised Pretraining (2021, background): “Furthermore, several recent papers that apply self-supervised learning to domain-specific problems did not apply transfer learning to the pretraining process itself, which motivated our work [57, 1, 29].”
Self-Supervised Learning in Remote Sensing: A review (2022, background): “[133]: inpainting, relative position and instance discrimination”
FALSE: False Negative Samples Aware Contrastive Learning for Semantic Segmentation of High-Resolution Remote Sensing Image (2022, unknown): “The experiments follow the general paradigm of SSL models [9], [11], [13] and are divided into two main steps: self-supervised pretraining and supervised ﬁne-tuning.”
Self-Supervised Learning of Remote Sensing Scene Representations Using Contrastive Multiview Coding (2021, background): “In [35] the authors analyze possibilities of using different self-supervised methods, specifically the ones based on image inpainting [27], context prediction [7], and contrastive learning using different augmentations.”
Unsupervised Single-Scene Semantic Segmentation for Earth Observation (2022, background): “Weakly supervised [48], [51], [52], unsupervised [53], and self-supervised learning [54], [55] have also been used in many remote sensing applications, e.”
Self-Supervised Representation Learning: Introduction, advances, and challenges (2021, unknown): “Beyond common benchmarks, SSRL has been successfully applied in application areas where labeled data are sparse, such as Earth-observation remote sensing [74].”
Self-Supervised Remote Sensing Feature Learning: Learning Paradigms, Challenges, and Future Works (2022, methodology): “[74] first applied the instance-level contrastive self-supervised method (i.”
Continual Contrastive Learning for Cross-Dataset Scene Classification (2022, background): “[24] pre-train a high-performance feature extract model from large unlabeled images and demonstrate that contrastive learning outperforms pre-training on the ImageNet dataset.”