A Deformable Convolutional Neural Network with Spatial-Channel Attention for Remote Sensing Scene Classification

Wang, Di; Lan, Jinhui

doi:10.3390/rs13245076

Cited by 11 publications

(4 citation statements)

References 44 publications

(53 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wang et al (2022a) proposed a single-CNN method for fusing multi-level features of a ResNeXt with semantic clustering. Wang and Lan (2021) and Miao et al (2023) proposed similar single-CNN methods for fusing the deformed or decoupled features. Bi et al (2022) proposed a single-CNN method by fusing reformulated features through a so-called multigrain-perception module.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

MBC-Net: long-range enhanced feature fusion for classifying remote sensing images

Song

2023

IJICC

View full text Add to dashboard Cite

PurposeClassification of remote sensing images (RSI) is a challenging task in computer vision. Recently, researchers have proposed a variety of creative methods for automatic recognition of RSI, and feature fusion is a research hotspot for its great potential to boost performance. However, RSI has a unique imaging condition and cluttered scenes with complicated backgrounds. This larger difference from nature images has made the previous feature fusion methods present insignificant performance improvements.Design/methodology/approachThis work proposed a two-convolutional neural network (CNN) fusion method named main and branch CNN fusion network (MBC-Net) as an improved solution for classifying RSI. In detail, the MBC-Net employs an EfficientNet-B3 as its main CNN stream and an EfficientNet-B0 as a branch, named MC-B3 and BC-B0, respectively. In particular, MBC-Net includes a long-range derivation (LRD) module, which is specially designed to learn the dependence of different features. Meanwhile, MBC-Net also uses some unique ideas to tackle the problems coming from the two-CNN fusion and the inherent nature of RSI.FindingsExtensive experiments on three RSI sets prove that MBC-Net outperforms the other 38 state-of-the-art (STOA) methods published from 2020 to 2023, with a noticeable increase in overall accuracy (OA) values. MBC-Net not only presents a 0.7% increased OA value on the most confusing NWPU set but also has 62% fewer parameters compared to the leading approach that ranks first in the literature.Originality/valueMBC-Net is a more effective and efficient feature fusion approach compared to other STOA methods in the literature. Given the visualizations of grad class activation mapping (Grad-CAM), it reveals that MBC-Net can learn the long-range dependence of features that a single CNN cannot. Based on the tendency stochastic neighbor embedding (t-SNE) results, it demonstrates that the feature representation of MBC-Net is more effective than other methods. In addition, the ablation tests indicate that MBC-Net is effective and efficient for fusing features from two CNNs.

show abstract

Section: Related Workmentioning

confidence: 99%

“…(2022a) proposed a single-CNN method for fusing multi-level features of a ResNeXt with semantic clustering. Wang and Lan (2021) and Miao et al. (2023) proposed similar single-CNN methods for fusing the deformed or decoupled features.…”

Section: Related Workmentioning

confidence: 99%

MBC-Net: long-range enhanced feature fusion for classifying remote sensing images

Song

2023

IJICC

View full text Add to dashboard Cite

show abstract

“…Although excellent results have been achieved in RS scene classification [39]- [41], there are still great challenges. Due to the special acquisition method, RS images present the characteristics of multi-scale, multi-target, and complex structures [42]. Therefore, in order to build a distinguishing feature representation, Xu et al take advantage of the feature fusion strategy by multi-layers for RS scene classification [43].…”

Section: Introductionmentioning

confidence: 99%

Attention-Aware Deep Feature Embedding for Remote Sensing Image Scene Classification

Chen

Han

et al. 2023

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

View full text Add to dashboard Cite

Due to the wide application of Remote Sensing (RS) image scene classification, more and more scholars activate great attention to it. With the development of the Convolutional Neural Network (CNN), the CNN-based methods of RS image scene classification have made impressive progress. In the existing works, most of the architectures just considered the global information of the RS images. However, the global information contains a large number of redundant areas that diminish the classification performance and ignore the local information that reflects more fine spatial details of local objects. Furthermore, most CNN-based methods assign the same weights to each feature vector causing the mode to fail to discriminate the crucial features. In this paper, a novel method by Two-branch Deep Feature Embedding with a Dual Attention-Aware module for RS image scene classification is proposed. In order to mine more complementary information, we extract global semanticbased features of high level and local object-based features of low level by the Two-branch Deep Feature Embedding (TDFE) module. Then, to focus selectively on the key global-semantics feature maps as well as the key local regions, we propose a Dual Attention-Aware (DAA) module to attain those key information. We conduct extensive experiments to verify the superiority of our proposed method, and the experimental results obtained on two widely used RS scene classification benchmarks demonstrate the effectiveness of the proposed method.

show abstract

“…Yin et al proposed a convolutional neural network based on attention mechanism, which integrates the interaction between sentences into CNN for modeling and recognition in natural language processing [17]. CNN has subsequently been well applied in the optimization convolution research of various feature patterns, including single line-to-ground fault detection [18], remote sensing scene classification [19], etc.…”

Section: Introductionmentioning

confidence: 99%

A Convolutional Neural Network Based on Attention Mechanism for Designing Vibration Similarity Models of Converter Transformers

Wang,

Zhang,

Sun

et al. 2023

Machines

View full text Add to dashboard Cite

A vibration scale training model for converter transformers is proposed by combining attention modules with convolutional neural networks to solve the nonlinear problem of converter transformers in similar processes. Firstly, according to the structure and operating parameters of the converter transformer, a reliable three-dimensional multi-field coupled finite element model was established considering the influence of the winding and iron core component structure on the overall vibration characteristics. By changing different input parameters such as the size and voltage of the finite element model, corresponding output parameters are obtained, and a dataset is established through data expansion for training and verifying the attention convolution model. By analyzing the prediction processes and results of five prediction models on different operating conditions datasets, it is shown that attention convolution has higher accuracy, faster convergence speed, more stable training process, and better generalization performance in the prediction process of converter transformer recognition. Based on the predictive model, a prototype of the proportional vibration model for the converter transformer with scale factor of 0.2 was designed and manufactured. By analyzing the basic experimental items and vibration characteristics of the prototype, the stability of the prototype and the reliability of the prediction model were verified.

show abstract

A Deformable Convolutional Neural Network with Spatial-Channel Attention for Remote Sensing Scene Classification

Cited by 11 publications

References 44 publications

MBC-Net: long-range enhanced feature fusion for classifying remote sensing images

MBC-Net: long-range enhanced feature fusion for classifying remote sensing images

Attention-Aware Deep Feature Embedding for Remote Sensing Image Scene Classification

A Convolutional Neural Network Based on Attention Mechanism for Designing Vibration Similarity Models of Converter Transformers

Contact Info

Product

Resources

About