Multiscale Residual Network With Mixed Depthwise Convolution for Hyperspectral Image Classification

Gao, Hongmin; Yang, Yuwei; Li, Chenming; Gao, Lianru; Zhang, Bing

doi:10.1109/tgrs.2020.3008286

Cited by 100 publications

(56 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Through this skip connection strategy, the residual networks can build very deep network structures without worrying about the gradients vanishing problem. The deep residual networks have been exploited for HSI classification, which can obtain superior classification accuracy than the CNN based methods [18], [19], [29], [39].…”

Section: A Residual Learningmentioning

confidence: 99%

“…The hierarchical multiscale CNN with the auxiliary classifier (HMCNN-AC) extracts multi-scale features from image patches of different sizes, and bidirectional long-short-term-memory (LSTM) considers these features as sequential data to capture dependence and correlation [28]. In [29], the multiscale residual network (MSRN) utilizes depthwise separable convolution (DSC) to construct multiscale residual block (MRB), and two MRBs are connected by high-level shortcut to aggregate features of different levels.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

HResNetAM: Hierarchical Residual Network With Attention Mechanism for Hyperspectral Image Classification

Xue

Liu

et al. 2021

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

View full text Add to dashboard Cite

This article proposes a novel hierarchical residual network with attention mechanism (HResNetAM) for hyperspectral image spectral-spatial classification to improve the performance of conventional deep learning networks. The straightforward convolutional neural network based models have limitations in exploiting the multi-scale spatial and spectral features, and this is the key factor in dealing with the high-dimensional nonlinear characteristics present in hyperspectral images. The proposed hierarchical residual network can extract multi-scale spatial and spectral features at a granular level, so the receptive fields range of this network will be increased, which can enhance the feature representation ability of the model. Besides, we utilize the attention mechanism to set adaptive weights for spatial and spectral features of different scales, and this can further improve the discriminative ability of extracted features. Furthermore, the double branch structure is also exploited to extract spectral and spatial features with corresponding convolution kernels in parallel, and the extracted spatial and spectral features of multiple scales are fused for hyperspectral image classification. Four benchmark hyperspectral datasets collected by different sensors and at different acquisition time are employed for classification experiments, and comparative results reveal that the proposed method has competitive advantages in terms of classification performance when compared with other state-ofthe-art deep learning models.

show abstract

Section: A Residual Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

HResNetAM: Hierarchical Residual Network With Attention Mechanism for Hyperspectral Image Classification

Xue

Liu

et al. 2021

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

View full text Add to dashboard Cite

show abstract

“…Compared with 1D-CNN and 2D-CNN models, 3D-CNN model is more suitable for processing three-dimensional HSI classification problem; it not only can extract features of spectral dimension but also simultaneous implement representation of spatial features, of which there are also many works that have made excellent research on solving the problem of small samples of hyperspectral, such as Gao et al, who proposed a new multi-scale residual network (MSRN) that introduces deep separable convolution (DSC) and replaces ordinary convolution with mixed deep convolution. The DSC with mixed deep convolution can explore features of different scales from each feature map and can also greatly reduce the learnable parameters in the network [30]. Multiscale dynamic graph convolutional network (MCGCN) is proposed, and it can conduct the convolution on arbitrarily structured non-Euclidean data and is applicable to the irregular image regions [31].…”

Section: Introductionmentioning

confidence: 99%

A Spectral Spatial Attention Fusion with Deformable Convolutional Residual Network for Hyperspectral Image Classification

et al. 2021

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) have exhibited excellent performance in hyperspectral image classification. However, due to the lack of labeled hyperspectral data, it is difficult to achieve high classification accuracy of hyperspectral images with fewer training samples. In addition, although some deep learning techniques have been used in hyperspectral image classification, due to the abundant information of hyperspectral images, the problem of insufficient spatial spectral feature extraction still exists. To address the aforementioned issues, a spectral–spatial attention fusion with a deformable convolution residual network (SSAF-DCR) is proposed for hyperspectral image classification. The proposed network is composed of three parts, and each part is connected sequentially to extract features. In the first part, a dense spectral block is utilized to reuse spectral features as much as possible, and a spectral attention block that can refine and optimize the spectral features follows. In the second part, spatial features are extracted and selected by a dense spatial block and attention block, respectively. Then, the results of the first two parts are fused and sent to the third part, and deep spatial features are extracted by the DCR block. The above three parts realize the effective extraction of spectral–spatial features, and the experimental results for four commonly used hyperspectral datasets demonstrate that the proposed SSAF-DCR method is superior to some state-of-the-art methods with very few training samples.

show abstract

“…He et al 10 used transfer learning to obtain hyperspectral image representation. Gao et al 11 explored the multi-scale residual network based on mixed convolution to obtain fusion features. Lu et al 12 presented a multi-scale residual network based on channel and spatial attention to perform hyperspectral image classification.…”

Section: Introductionmentioning

confidence: 99%

Asymmetric coordinate attention spectral-spatial feature fusion network for hyperspectral image classification

Cheng

Wang

2021

Sci Rep

View full text Add to dashboard Cite

In recent years, the hyperspectral classification algorithm based on deep learning has received widespread attention, but the existing network models have higher model complexity and require more time consumption. In order to further improve the accuracy of hyperspectral image classification and reduce model complexity, this paper proposes an asymmetric coordinate attention spectral-spatial feature fusion network (ACAS2F2N) to capture distinguishing hyperspectral features. Specifically, adaptive asymmetric iterative attention was proposed to obtain the discriminative spectral-spatial features. Different from the common feature fusion method, this feature fusion method can adapt to most skip connection tasks. In addition, there is no manual parameter setting. Coordinate attention is used to obtain accurate coordinate information and channel relationship. The strip pooling module was introduced to increase the network’s receptive field and avoid irrelevant information brought by conventional convolution kernels. The proposed algorithm is tested on the mainstream hyperspectral datasets (IP, KSC, and Botswana), experimental results show that the proposed ACAS2F2N can achieve state-of-the-art performance with lower time complexity.

show abstract

Multiscale Residual Network With Mixed Depthwise Convolution for Hyperspectral Image Classification

Cited by 100 publications

References 41 publications

HResNetAM: Hierarchical Residual Network With Attention Mechanism for Hyperspectral Image Classification

HResNetAM: Hierarchical Residual Network With Attention Mechanism for Hyperspectral Image Classification

A Spectral Spatial Attention Fusion with Deformable Convolutional Residual Network for Hyperspectral Image Classification

Asymmetric coordinate attention spectral-spatial feature fusion network for hyperspectral image classification

Contact Info

Product

Resources

About