Remote Sensing Scene Classification Research Articles

Evaluation of Ten Deep-Learning-Based Out-of-Distribution Detection Methods for Remote Sensing Image Scene Classification

Although deep neural networks have made significant progress in tasks related to remote sensing image scene classification, most of these tasks assume that the training and test data are independently and identically distributed. However, when remote sensing scene classification models are deployed in the real world, the model will inevitably encounter situations where the distribution of the test set differs from that of the training set, leading to unpredictable errors during the inference and testing phase. For instance, in the context of large-scale remote sensing scene classification applications, it is difficult to obtain all the feature classes in the training phase. Consequently, during the inference and testing phases, the model will categorize images of unidentified unknown classes into known classes. Therefore, the deployment of out-of-distribution (OOD) detection within the realm of remote sensing scene classification is crucial for ensuring the reliability and safety of model application in real-world scenarios. Despite significant advancements in OOD detection methods in recent years, there remains a lack of a unified benchmark for evaluating various OOD methods specifically in remote sensing scene classification tasks. We designed different benchmarks on three classical remote sensing datasets to simulate scenes with different distributional shift. Ten different types of OOD detection methods were employed, and their performance was evaluated and compared using quantitative metrics. Numerous experiments were conducted to evaluate the overall performance of these state-of-the-art OOD detection methods under different test benchmarks. The comparative results show that the virtual-logit matching methods without additional training outperform the other types of methods on our benchmarks, suggesting that additional training methods are unnecessary for remote sensing image scene classification applications. Furthermore, we provide insights into OOD detection models and performance enhancement in real world. To the best of our knowledge, this study is the first evaluation and analysis of methods for detecting out-of-distribution data in remote sensing. We hope that this research will serve as a fundamental resource for future studies on out-of-distribution detection in remote sensing.

Advancements in Self-Supervised Learning for Remote Sensing Scene Classification: Present Innovations and Future Outlooks

Deep learning methodologies have significantly advanced the fields of computer vision and machine learning, enhancing performance across various tasks like classification, regression, and detection. In remote sensing for Earth observation, deep neural networks have propelled state-of-the-art results. However, a major drawback is their dependence on large annotated datasets, necessitating extensive human effort, especially in specialized domains like medical imaging or remote sensing. To mitigate this reliance on annotations, several self-supervised representation learning techniques have emerged, aiming to learn unsupervised image representations applicable to downstream tasks such as image classification, object detection, or semantic segmentation. Consequently, self-supervised learning approaches have gained traction in remote sensing. This article surveys the foundational principles of various self-supervised methods, focusing on scene classification tasks. We elucidate key contributions, analyze experimental setups, and synthesize findings from each study. Furthermore, we conduct comprehensive experiments on two public scene classification datasets to evaluate and benchmark different self-supervised models

Advancements in Self-Supervised Learning for Remote Sensing Scene Classification: Present Innovations and Future Outlooks

Deep learning methodologies have significantly advanced the fields of computer vision and machine learning, enhancing performance across various tasks like classification, regression, and detection. In remote sensing for Earth observation, deep neural networks have propelled state-of-the-art results. However, a major drawback is their dependence on large annotated datasets, necessitating extensive human effort, especially in specialized domains like medical imaging or remote sensing. To mitigate this reliance on annotations, several self-supervised representation learning techniques have emerged, aiming to learn unsupervised image representations applicable to downstream tasks such as image classification, object detection, or semantic segmentation. Consequently, self-supervised learning approaches have gained traction in remote sensing. This article surveys the foundational principles of various self-supervised methods, focusing on scene classification tasks. We elucidate key contributions, analyze experimental setups, and synthesize findings from each study. Furthermore, we conduct comprehensive experiments on two public scene classification datasets to evaluate and benchmark different self-supervised models

LPNet: A remote sensing scene classification method based on large kernel convolution and parameter fusion

LPNet: A remote sensing scene classification method based on large kernel convolution and parameter fusion

Frequency and spatial based multi-layer context network (FSCNet) for remote sensing scene classification

Remote Sensing Scene Classification (RSSC) is an important and challenging research topic due to the variety of land cover sizes and spatial combinations, as well as significant interclass similarity and intraclass variability. Currently, convolutional neural network (CNN)-based methods have been widely used in RSSC tasks with significant results. However, CNNs lack the ability to obtain long-term correlations. Transformer addressed this problem, thanks to the global receptive field of multi-head self-attention (MSA). Nevertheless, the vanilla transformer also needs further improvement to accommodate the diverse in type and scale of objects in RS scenes. In addition, the existing RSSC methods either use the last layer features, which is not conducive to process multi-scale remote sensing images, or directly fuse the multi-layer features, which will bring redundant or mutually exclusive information. To address the above issues, a novel RSSC framework, named frequency and spatial based multi-layer attention network (FSCNet) for remote sensing scene classification is proposed in this article. First, to fully extract the pyramid multi resolution features of CNN, a cross resolution injection model (CRIM) is proposed. Second, to generate better understand of the multilevel features, a frequency and spatial MLP (FS-MLP) is designed. Third, in order to aggregate contextual relations among multi-layer features, a multi-layer context align attention (MCAA) is adopted. The final classification is integration of top-layer feature and aggregated multi-layer feature. The experiment results on three well-known RS scene classification datasets (UCM, AID, and NWPU) prove the effectiveness of FSCNet and it outperforms many state-of-the-art methods.

DEEP LEARNING-BASED SCENE CLASSIFICATION OF VERY HIGH-RESOLUTION SATELLITE IMAGERY FOR POST-EARTHQUAKE DAMAGE ASSESSMENT: A CASE STUDY OF THE 2023 KAHRAMANMARAŞ EARTHQUAKES

Abstract. Following the devastating earthquakes in Kahramanmaraş province, Türkiye, on February 6, 2023, which resulted in the loss of over 50,000 lives and damage to more than 84,000 buildings, the pressing need for efficient damage assessment and response became apparent. Traditional on-site assessments are time-consuming and perilous. Most existing research leans towards segmentation and object detection methods for earthquake damage assessment using remotely sensed data, which demand substantial training data, computational resources, and time. A more practical approach can be classifying image patches to identify earthquake-affected areas with damaged buildings. This scene classification method categorizes image patches based on their content. Remote sensing scene classification assigns labels to such images using deep learning various algorithms. In this work, we developed a fully automated system utilizing Maxar’s very high-resolution post-earthquake satellite imagery to classify and map the scenes (image patches) involving collapsed and non-collapsed buildings in Antakya and Iskenderun city centers. Our approach involved two key scene classifiers: Classifier #1, employing deep learning models like ResNet-101, effectively detected building presence within the image scene with remarkable accuracy (99.17%). This classifier served as the foundation for identifying the scenes involving buildings for entire city in order to filter the non-urban land use. Then, Classifier #2, classified building scenes into collapsed and non-collapsed categories. The DenseNet-121 model excelled, achieving an accuracy of 93.33% in this task. In the end, Classifier #2 categorized 2,429 non-collapsed and 449 collapsed scenes in Antakya and 2,291 non-collapsed and 290 collapsed scenes in Iskenderun.

Synthetic aperture radar remote sensing scene classification based on fuzzy co-occurrence networks

Synthetic aperture radar remote sensing scene classification based on fuzzy co-occurrence networks

Integrating category-related key regions with a dual-stream network for remote sensing scene classification

Remote sensing image scene classification has made great progress with deep learning. Due to complex backgrounds and the large number of objects with inhomogeneous sizes, remote sensing image scene classification still remains challenging. In fact, only a few parts of regions are expected to be representative of the scene. In this paper, we propose a dual-stream framework for remote sensing classification with the help of category-related regions. Swin Transformer-based global feature extractor is used to produce coarse classification results. A category-related key region localization module is developed to extract the representative region from the whole image. The ResNet50 is employed as a local feature extractor to mine critical features from prominent regions. Finally, the classification results is obtained with the shared weighted classify head on global-local features. Extensive experiments show that our method provides a promising approach for key region locations and performs best on three public remote sensing datasets.

Multi-View Scene Classification Based on Feature Integration and Evidence Decision Fusion

Leveraging multi-view remote sensing images in scene classification tasks significantly enhances the precision of such classifications. This approach, however, poses challenges due to the simultaneous use of multi-view images, which often leads to a misalignment between the visual content and semantic labels, thus complicating the classification process. In addition, as the number of image viewpoints increases, the quality problem for remote sensing images further limits the effectiveness of multi-view image classification. Traditional scene classification methods predominantly employ SoftMax deep learning techniques, which lack the capability to assess the quality of remote sensing images or to provide explicit explanations for the network’s predictive outcomes. To address these issues, this paper introduces a novel end-to-end multi-view decision fusion network specifically designed for remote sensing scene classification. The network integrates information from multi-view remote sensing images under the guidance of image credibility and uncertainty, and when the multi-view image fusion process encounters conflicts, it greatly alleviates the conflicts and provides more reasonable and credible predictions for the multi-view scene classification results. Initially, multi-scale features are extracted from the multi-view images using convolutional neural networks (CNNs). Following this, an asymptotic adaptive feature fusion module (AAFFM) is constructed to gradually integrate these multi-scale features. An adaptive spatial fusion method is then applied to assign different spatial weights to the multi-scale feature maps, thereby significantly enhancing the model’s feature discrimination capability. Finally, an evidence decision fusion module (EDFM), utilizing evidence theory and the Dirichlet distribution, is developed. This module quantitatively assesses the uncertainty in the multi-perspective image classification process. Through the fusing of multi-perspective remote sensing image information in this module, a rational explanation for the prediction results is provided. The efficacy of the proposed method was validated through experiments conducted on the AiRound and CV-BrCT datasets. The results show that our method not only improves single-view scene classification results but also advances multi-view remote sensing scene classification results by accurately characterizing the scene and mitigating the conflicting nature of the fusion process.

Remote sensing scene classification using multi-domain sematic high-order network

Recently, convolutional neural networks (CNNs), which obtain powerful deep features in an end-to-end manner, have achieved powerful performance in remote sensing scene classification. However, the average or maximum pooling operations defined in the spatial domain and coarser-resolution features with high levels cannot extract reliable features and clear boundaries for small-scale targets in remote sensing scene imagery. This paper attempts to address these problems and proposes a multi-domain sematic high-order network for scene classification, named MSHNet. First, wavelet-spatial and detachable pooling blocks defined in the wavelet and spatial domains are inserted at the end of the convolutional block to learn the features in a more structural fusion manner. Second, multi-scale and multi-resolution semantic embedding modules are proposed to take full advantage of the complementary information and effectively maintain the spatial structures of learned deep features. Third, we employ a factorized bilinear coding approach to obtain compact and discriminative second-order features. MSHNet is thoroughly evaluated on two publicly available benchmarks, i.e., AID (Aerial Image Dataset) and NWPU-RESISC45 (Northwestern Polytechnical University-Remote Sensing Image Scene Classification 45). The extensive results illustrate that our MSHNet is competitive with other related multi-scale deep neural networks.

Optimizing distortion magnitude for data augmentation in few-shot remote sensing scene classification

ABSTRACT In the domain of few-shot classification tasks for remote sensing images, the impact of data augmentation is often overlooked, and conventional methods offer only modest gains in classification performance. To better exploit the potential of data augmentation in few-shot learning, we propose an innovative data augmentation method tailored to optimize few-shot remote sensing scene classification. We begin by dissecting the relationship between various types of feature distortions and classification performance, introducing an optimal distortion magnitude estimation method for different feature types. Subsequently, we integrate multiple distortion magnitude optimization pathways into the model learning process, achieving a dual optimization of model parameters and distortion magnitudes. The extended data provide the model with distorted samples from multiple feature perspectives, and the dynamic optimization of distortion magnitudes enhances the effectiveness of the extended data for classification. Ultimately, we evaluate the performance of our method on general remote sensing datasets, demonstrating a significant advantage in classification accuracy over baseline methods. This approach offers a new perspective in robustness research for few-shot remote sensing scene classification models based on data augmentation.

Optimizing Few-Shot Remote Sensing Scene Classification Based on an Improved Data Augmentation Approach

In the realm of few-shot classification learning, the judicious application of data augmentation methods has a significantly positive impact on classification performance. In the context of few-shot classification tasks for remote sensing images, the augmentation of features and the efficient utilization of limited features are of paramount importance. To address the performance degradation caused by challenges such as high interclass overlap and large intraclass variance in remote sensing image features, we present a data augmentation-based classification optimization method for few-shot remote sensing image scene classification. First, we construct a distortion magnitude space using different types of features, and we perform distortion adjustments on the support set samples while introducing an optimal search for the distortion magnitude (ODS) method. Then, the augmented support set offers a wide array of feature distortions in terms of types and degrees, significantly enhancing the generalization of intrasample features. Subsequently, we devise a dual-path classification (DC) decision strategy, effectively leveraging the discriminative information provided by the postdistortion features to further reduce the likelihood of classification errors. Finally, we evaluate the proposed method using a widely used remote sensing dataset. Our experimental results demonstrate that our approach outperforms benchmark methods, achieving improved classification accuracy.

MSE-Net: A novel master–slave encoding network for remote sensing scene classification

Remote sensing scene (RSS) image classification plays a vital role in various fields such as urban planning and environmental protection. However, due to higher inter-class similarity and intra-class variability, achieving accurate classification for RSS images poses a considerable challenge for current convolutional neural networks (CNNs)-based and visual transformer (ViT)-based methods. To address these issues, this paper proposes a novel dual-encoding method named master–slave encoding network (MSE-Net) from two perspectives of feature extraction and fusion. The master encoder, based on ViT, extracts higher-level semantic features, while the slave encoder, based on CNN, captures relative lower-level spatial structure information. Secondly, to integrate feature information from the two encoders effectively, this paper further develop two fusion strategies. The first strategy involves the auxiliary enhancement units (AEUs), which eliminates semantic divergence between the two encoders, enhances spatial context awareness of the slave encoder and promotes effective feature learning. The interactive perception unit (IPU), as the second strategy, facilitates interaction and integration of the two encoders’ representations to extract more discriminative feature information. In addition, we conducted comparative experiments on four widely-used RSS datasets, including RSSCN7, SIRI-WHU, the aerial image dataset (AID) and NWPU-RESISC45 (NWPU45), to verify the effectiveness of MSE-Net. The experimental results demonstrate that MSE-Net achieved state-of-the-art (SOTA) performance across all the datasets.

A hybrid CNN–vision transformer structure for remote sensing scene classification

ABSTRACT Vision Transformers (ViTs) have become one of the main architectures in deep learning with the self-attention mechanism, and are becoming an alternative to Convolutional Neural Networks (CNNs) for remote sensing scene classification tasks. However, the earlier self-attention layer of ViTs focuses on local features rather than global features, and the deeper self-attention layer focuses on global features but ignores the different impact of different frequency information. This will greatly increase the training and computational cost due to the quadratic complexity of the self-attention mechanism on the long sequence representation. In this paper, we propose a hybrid CNN – vision transformer structure (HCVNet), which uses convolutional layers to replace the earlier self-attention layers, and a novel Frequency Multi-head Self Attention (F-MSA) mechanism to replace the deeper self-attention layers. Specifically, F-MSA is a dual-stream structure that reduces the computational cost and improves the classification performance by encoding the high/low frequency information separately. In addition, a Semantic-aware Localization (SaL) module is introduced, which can guide the selection of crop by learning prior knowledge, avoiding the issue of pure background sampling. Our method performed an accuracy value of 97.20 ± 0.02% on the Aerial Image Dataset and 93.89 ± 0.03% on the NWPU-RESISC45 Dataset, with low complexity costs.

Distortion Magnitude Control: A Dynamic Augmentation Optimization Approach for Few-Shot Learning in Remote Sensing Scene Classification

Distortion Magnitude Control: A Dynamic Augmentation Optimization Approach for Few-Shot Learning in Remote Sensing Scene Classification

Gradient Guided Multiscale Feature Collaboration Networks for Few-Shot Class-Incremental Remote Sensing Scene Classification

Gradient Guided Multiscale Feature Collaboration Networks for Few-Shot Class-Incremental Remote Sensing Scene Classification

Zero-Shot Remote Sensing Scene Classification Method Based on Local-Global Feature Fusion and Weight Mapping Loss

Zero-Shot Remote Sensing Scene Classification Method Based on Local-Global Feature Fusion and Weight Mapping Loss

Co-Enhanced Global-Part Integration for Remote-Sensing Scene Classification

Co-Enhanced Global-Part Integration for Remote-Sensing Scene Classification

Diversity-Infused Network for Unsupervised Few-Shot Remote Sensing Scene Classification

Diversity-Infused Network for Unsupervised Few-Shot Remote Sensing Scene Classification

Localizing From Classification: Self-Directed Weakly Supervised Object Localization for Remote Sensing Images.

In recent years, object localization and detection methods in remote sensing images (RSIs) have received increasing attention due to their broad applications. However, most previous fully supervised methods require a large number of time-consuming and labor-intensive instance-level annotations. Compared with those fully supervised methods, weakly supervised object localization (WSOL) aims to recognize object instances using only image-level labels, which greatly saves the labeling costs of RSIs. In this article, we propose a self-directed weakly supervised strategy (SD-WSS) to perform WSOL in RSIs. To specify, we fully exploit and enhance the spatial feature extraction capability of the RSIs' classification model to accurately localize the objects of interest. To alleviate the serious discriminative region problem exhibited by previous WSOL methods, the spatial location information implicit in the classification model is carefully extracted by GradCAM ++ to guide the learning procedure. Furthermore, to eliminate the interference from complex backgrounds of RSIs, we design a novel self-directed loss to make the model optimize itself and explicitly tell it where to look. Finally, we review and annotate the existing remote sensing scene classification dataset and create two new WSOL benchmarks in RSIs, named C45V2 and PN2. We conduct extensive experiments to evaluate the proposed method and six mainstream WSOL methods with three backbones on C45V2 and PN2. The results demonstrate that our proposed method achieves better performance when compared with state-of-the-arts.