A Novel Deep Feature Fusion Network For Remote Sensing Scene Classification

Li, Yangyang; Wang, Qi; Liang, Xiaoxu; Jiao, Licheng

doi:10.1109/igarss.2019.8898900

Cited by 14 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has achieved great success in remote sensing scene image classification, and many CNNbased methods have been proposed. For example, Li et al [27] proposed a deep feature fusion network for remote sensing scene classification. Zhao et al [28] proposed a structure that combines local spectral features, global texture features, and local structural features to fuse features.…”

Section: Classification Of Remote Sensing Scene Imagesmentioning

confidence: 99%

Learn by Yourself: A Feature-Augmented Self-Distillation Convolutional Neural Network for Remote Sensing Scene Image Classification

Shi,

Ding,

Wang

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

In recent years, with the rapid development of deep learning technology, great progress has been made in remote sensing scene image classification. Compared with natural images, remote sensing scene images are usually more complex, with high inter-class similarity and large intra-class differences, which makes it difficult for commonly used networks to effectively learn the features of remote sensing scene images. In addition, most existing methods adopt hard labels to supervise the network model, which makes the model prone to losing fine-grained information of ground objects. In order to solve these problems, a feature-augmented self-distilled convolutional neural network (FASDNet) is proposed. First, ResNet34 is adopted as the backbone network to extract multi-level features of images. Next, a feature augmentation pyramid module (FAPM) is designed to extract and fuse multi-level feature information. Then, auxiliary branches are constructed to provide additional supervision information. The self-distillation method is utilized between the feature augmentation pyramid module and the backbone network, as well as between the backbone network and auxiliary branches. Finally, the proposed model is jointly supervised using feature distillation loss, logits distillation loss, and cross-entropy loss. A lot of experiments are conducted on four widely used remote sensing scene image datasets, and the experimental results show that the proposed method is superior to some state-ot-the-art classification methods.

show abstract

Section: Classification Of Remote Sensing Scene Imagesmentioning

confidence: 99%

Learn by Yourself: A Feature-Augmented Self-Distillation Convolutional Neural Network for Remote Sensing Scene Image Classification

Shi,

Ding,

Wang

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The high-level features have stronger semantic information, however, resolution is low, and detail perception is typically poor. Several studies have shown that fusing the features of different convolutional layers can enhance feature representation and improve image classification performance [5,6,19]. Lin et al [19] used a multi-level feature fusion architecture to enhance the discriminator's discriminant ability for improving the performance of unsupervised classification.…”

Section: E Spectral Normalization and Multi-level Feature Fusionmentioning

confidence: 99%

“…R EMOTE sensing image scene classification has always been a hot spot in the field of remote sensing image interpretation and can automatically classify scene images into a group of pre-defined semantic categories based on the image content [1]. Supervised learning-based deep neural networks have shown outstanding performance on scene classification of remote sensing images [2]- [6]. Typically, supervised methods require a large sets of tagged examples to obtain higher prediction performance.…”

Section: Introductionmentioning

confidence: 99%

“…Duta et al [26] introduced pyramidal convolution (PyConv) to leverage different types of filters with different sizes and depths to obtain more discriminant feature representation and improve image classification performance. Additionally, several studies have shown that fusing the features of different convolutional layers can enhance feature representation and improve image classification performance [5,6,19]. Lin et al [19] used multilevel feature fusion to merge midlevel and global features, and fit the complex properties of remote sensing images to learn more discriminant feature representations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Self-Supervised GANs With Similarity Loss for Remote Sensing Image Scene Classification

Guo

Xia

Luo

2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

With the development of supervised deep neural networks, classification performance on existing remote sensing scene datasets has been markedly improved. However, supervised learning methods rely heavily on large-scale tagged examples to obtain a better prediction performance. The lack of large-scale tagged remote sensing scene images has become the primary bottleneck in scene classification. To deal with this issue, a novel scene classification method using self-supervised gated self-attention generative adversarial networks (SGSAGANs) with similarity loss is proposed. Specifically, the gated self-attention module is first introduced into GANs to focus on key scene areas and filter useless information for strengthening feature representations. Then, the pyramidal convolution (PyConv) block is introduced into the residual block of the discriminator to capture different levels of details in the image using different types of filters with varying sizes and depths for enhancing the feature representations of the discriminator. Additionally, a novel similarity loss item is integrated into the discriminator to leverage self-supervised learning. Besides, spectral normalization is introduced into both the generative network and discriminative network to stabilize training and enhance feature representations. The architecture of multi-level feature fusion is integrated into the discriminative network to achieve more discriminant representation. Experimental results on the AID and NWPU-RESISC45 datasets show that the proposed method achieves the best performance compared to the existing unsupervised classification methods.

show abstract

“…Fang et al adopted the pre-trained CaffeNet model with fine-tuning, the proposed method was robust and efficient [40]. Liu features from pre-trained and fine-tuned ResNet50 and VGG16 [42]. Tian et al proposed a CapsNet-based network structure called Res-CapsNet for RS scene classification, and achieved improved performance [43].…”

Section: Introductionmentioning

confidence: 99%

Remote Sensing Scene Classification Using Sparse Representation-Based Framework With Deep Feature Fusion

Mei

Yan

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Scene classification of high resolution remote sensing (RS) images has attracted increasing attentions due to its vital role in a wide range of applications. Convolutional Neural Networks (CNNs) have recently been applied on many computer vision tasks and have significantly boosted the performance including imagery scene classification, object detection and so on. However, classification performance heavily relies on the features that can accurately represent the scene of images, thus, how to fully explore the feature learning ability of CNNs is of crucial importance for scene classification. Another problem in CNNs is that it requires a large number of labeled samples, which is impractical in RS image processing. To address these problems, a novel sparse representation-based framework for small-samplesize RS scene classification with deep feature fusion is proposed. Specially, multi-level features are first extracted from different layers of CNNs to fully exploit the feature learning ability of CNNs. Note that the existing well-trained CNNs, e.g., AlexNet, VGGNet, and ResNet50, are used for feature extraction, in which no labeled samples is required. Then, sparse representation-based classification is designed to fuse the multi-level features, which is especially effective when only a small number of training samples are available. Experimental results over two benchmark datasets, e.g., UC-Merced and WHU-RS19, demonstrated that the proposed method can effectively fuse different levels of features learned in CNNs, and clearly outperform several state-of-the-art methods especially with limited training samples.

show abstract

A Novel Deep Feature Fusion Network For Remote Sensing Scene Classification

Cited by 14 publications

References 9 publications

Learn by Yourself: A Feature-Augmented Self-Distillation Convolutional Neural Network for Remote Sensing Scene Image Classification

Learn by Yourself: A Feature-Augmented Self-Distillation Convolutional Neural Network for Remote Sensing Scene Image Classification

Self-Supervised GANs With Similarity Loss for Remote Sensing Image Scene Classification

Remote Sensing Scene Classification Using Sparse Representation-Based Framework With Deep Feature Fusion

Contact Info

Product

Resources

About