Scene Classification of Remote Sensing Images Based on Saliency Dual Attention Residual Network

Guo, Dongen; Xia, Ying; Luo, Xiaobo

doi:10.1109/access.2019.2963769

Cited by 34 publications

(25 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another work in [43] propose a novel Saliency Dual Attention Residual Network (SDAResNet) to extract both cross-channel and spatial saliency information for scene classification of RSI. More specifically, spatial attention is embedded in low-level feature to emphasize saliency location information and suppress background information, and channel attention is integrated to high-level features to extract saliency meaningful information.…”

Section: Figurementioning

confidence: 99%

Classification of Remote Sensing Images Using EfficientNet-B3 CNN Model With Attention

et al. 2021

View full text Add to dashboard Cite

Scene classification is a highly useful task in Remote Sensing (RS) applications. Many efforts have been made to improve the accuracy of RS scene classification. Scene classification is a challenging problem, especially for large datasets with tens of thousands of images with a large number of classes and taken under different circumstances. One problem that is observed in scene classification is the fact that for a given scene, only one part of it indicates which class it belongs to, whereas the other parts are either irrelevant or they actually tend to belong to another class. To address this issue, this paper proposes a deep attention Convolutional Neural Network (CNN) for scene classification in remote sensing. CNN models use successive convolutional layers to learn feature maps from larger and larger regions (or receptive fields) of the scene. The attention mechanism computes a new feature map as a weighted average of these original feature maps. In particular, we propose a solution, named EfficientNet-B3-Attn-2, based on the pre-trained EfficientNet-B3 CNN enhanced with an attention mechanism. A dedicated branch is added to layer 262 of the network, to compute the required weights. These weights are learned automatically by training the whole CNN model end-to-end using the backpropagation algorithm. In this way, the network learns to emphasize important regions of the scene and suppress the regions that are irrelevant to the classification. We tested the proposed EfficientNet-B3-Attn-2 on six popular remote sensing datasets, namely UC Merced, KSA, OPTIMAL-31, RSSCN7, WHU-RS19, and AID datasets, showing its strong capabilities in classifying RS scenes.

show abstract

Section: Figurementioning

confidence: 99%

Classification of Remote Sensing Images Using EfficientNet-B3 CNN Model With Attention

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Also, the top(4, 3, 2, 1) denote the case when using only the fourth level of PyConv for the first D block (9 × 9 kernel), the third level for the 2nd D block (7 × 7 kernel), second level for the 3rd D block (5 × 5 kernel) and first level for the 4th D block (3 × 3 kernel). For levels (5,4,3,2), the fifth level has an 11 × 11 kernel.…”

Section: Ablation Studymentioning

confidence: 99%

“…The top(4, 3, 2, 1) also yield a significant performance improvement compared to the baseline, indicating that increasing the filter sizes when building PyConv is beneficial. Besides, we also experimented with levels (5,4,3,2), in which more levels are added to PyConv. In this case, the overall accuracy is lower than levels(4, 3, 2, 1), indicating that more levels in PyConv do not necessarily yield better performance.…”

Section: Ablation Studymentioning

confidence: 99%

“…Primarily inspired by [20] and [21], we further investigate methods that can be used in GANs to extract more discriminant features. Among these methods, vision attention mechanisms have been widely used for various visual tasks, such as image generation, semantic segmentation, and image classification [3,[23][24]. Wang et al [23] used a residual attention network to classify images.…”

Section: Introductionmentioning

confidence: 99%

“…Wang et al [23] used a residual attention network to classify images. Guo et al [3] leveraged a saliency dual attention residual network to conduct remote sensing image scene classification. Zhang et al [24] introduced self-attention into GANs to capture long-range dependency for generating more realistic images.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Self Cite

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

Classification of Indoor–Outdoor Scene Using Deep Learning Techniques

Kumar¹,

Gupta²,

Ingale³

et al. 2023

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Scene Classification of Remote Sensing Images Based on Saliency Dual Attention Residual Network

Cited by 34 publications

References 36 publications

Classification of Remote Sensing Images Using EfficientNet-B3 CNN Model With Attention

Classification of Remote Sensing Images Using EfficientNet-B3 CNN Model With Attention

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

Classification of Indoor–Outdoor Scene Using Deep Learning Techniques

Contact Info

Product

Resources

About