A Deep Neural Network Combined With Context Features for Remote Sensing Scene Classification

Deng, Peifang; Hong, Huixiao; Xu, Kejie

doi:10.1109/lgrs.2020.3016769

Cited by 9 publications

(7 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GoogLeNet [40] 94.31 ± 0.89 92.70 ± 0.60 VGG-16 [40] 95.21 ± 1.20 94.14 ± 0.69 CRAN [42] 95.75 ± 0.80 94.21 ± 0.75 MobileNet V2 [43] 99.01 ± 0.21 97.88 ± 0.31 SE-MDPMNet [44] 98.95 ± 0.12 98.36 ± 0.14 Two-Stream Fusion [45] 98.02 ± 1.03 96.97 ± 0.75 ViT [4] 99.29 ± 0.34 98.75 ± 0.21 CFDNN [46] 98.62 ± 0.27 97.65 ± 0.18 Inception-v3-CapsNet [18] 99.05 ± 0.24 97.59 ± 0.16 GSSF [47] 99.24 ± 0.47 97.86 ± 0.56 PCNet [48] 99.25 ± 0.37 98.71 ± 0.22 GAN [26] 98.58 ± 0.33 97.54 ± 0. As shown in Figure 7, the confusion matrix with all 21 classes was also created to further examine the performance of FCIHMRT with an 80% training ratio.…”

Section: Methods 80% Training Ratio (Oa) 50% Training Ratio (Oa)mentioning

confidence: 99%

FCIHMRT: Feature Cross-Layer Interaction Hybrid Method Based on Res2Net and Transformer for Remote Sensing Scene Classification

Huo,

Gang,

Guan

2023

Electronics

View full text Add to dashboard Cite

Scene classification is one of the areas of remote sensing image processing that is gaining much attention. Aiming to solve the problem of the limited precision of optical scene classification caused by complex spatial patterns, a high similarity between classes, and a high diversity of classes, a feature cross-layer interaction hybrid algorithm for optical remote sensing scene classification is proposed in this paper. Firstly, a number of features are extracted from two branches, a vision transformer branch and a Res2Net branch, to strengthen the feature extraction capability of the strategy. A novel interactive attention technique is proposed, with the goal of focusing on the strong correlation between the two-branch features, to fully use the complementing advantages of the feature information. The retrieved feature data are further refined and merged. The combined characteristics are then employed for classification. The experiments were conducted by using three open-source remote sensing datasets to validate the feasibility of the proposed method, which performed better in scene classification tasks than other methods.

show abstract

Section: Methods 80% Training Ratio (Oa) 50% Training Ratio (Oa)mentioning

confidence: 99%

FCIHMRT: Feature Cross-Layer Interaction Hybrid Method Based on Res2Net and Transformer for Remote Sensing Scene Classification

Huo,

Gang,

Guan

2023

Electronics

View full text Add to dashboard Cite

show abstract

“…Shi et al [32] proposed a dense fusion of multi-level features, through 3 × 3 depthwise separable convolution and 1 × 1 standard convolution, to extract the information of the current layer and fuse it with the features extracted from the previous layer. Deng et al [33] proposed a deep neural network incorporating contextual features, using the pre-trained VGG-16 as a feature extractor to obtain feature maps. Then, the feature map is input into two parallel modules, global average pooling (GAP) and long short-term memory (LSTM), to extract global and contextual features, respectively, and finally splicing global features and contextual 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

“…To limit the value of μ and λ to a certain range, the limiting condition is added that the sum of μ and λ is 2, as shown in formula (11). By studying the gradient of DICE and BCE, it is found that the loss of DICE is greater than that of BCE.…”

Section: Experiments On Weight Of Loss Functionmentioning

confidence: 99%

“…In recent years, deep learning has become a heated topic in the study of artificial intelligence. Deep learning theory represented by convolutional neural network typically has made some achievements in the field of image classification [9][10][11], semantic segmentation [12,13], feature extraction [14], smart grid [15,16], etc. e method based on a convolutional neural network is able to complete the modeling process through automatic learning of features, avoiding the incomplete modeling process caused by human intervention in the early stage.…”

Section: Introductionmentioning

confidence: 99%

River Segmentation of Remote Sensing Images Based on Composite Attention Network

et al. 2022

View full text Add to dashboard Cite

River segmentation of remote sensing images is of important research significance and application value for environmental monitoring, disaster warning, and agricultural planning in an area. In this study, we propose a river segmentation model in remote sensing images based on composite attention network to solve the problems of abundant river details in images and the interference of non-river information including bridges, shadows, and roads. To improve the segmentation efficiency, a composite attention mechanism is firstly introduced in the central region of the network to obtain the global feature dependence of river information. Next, in this study, we dynamically combine binary cross-entropy loss that is designed for pixel-wise segmentation and the Dice coefficient loss that measures the similarity of two segmentation objects into a weighted one to optimize the training process of the proposed segmentation network. The experimental results show that compared with other semantic segmentation networks, the evaluation indexes of the proposed method are higher than those of others, and the river segmentation effect of CoANet model is significantly improved. This method can segment rivers in remote sensing images more accurately and coherently, which can meet the needs of subsequent research.

show abstract

A Deep Neural Network Combined With Context Features for Remote Sensing Scene Classification

Cited by 9 publications

References 32 publications

FCIHMRT: Feature Cross-Layer Interaction Hybrid Method Based on Res2Net and Transformer for Remote Sensing Scene Classification

FCIHMRT: Feature Cross-Layer Interaction Hybrid Method Based on Res2Net and Transformer for Remote Sensing Scene Classification

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

River Segmentation of Remote Sensing Images Based on Composite Attention Network

Contact Info

Product

Resources

About