Attention-Based Adaptive Spectral–Spatial Kernel ResNet for Hyperspectral Image Classification

Roy, Swalpa Kumar; Manna, Suvojit; Song, Tianyou; Bruzzone, Lorenzo

doi:10.1109/tgrs.2020.3043267

Cited by 315 publications

(110 citation statements)

References 62 publications

Supporting

Mentioning

110

Contrasting

Order By: Relevance

“…Wang et al [14] proposed an end-to-end cubic CNN, which applies convolutions in different directions of the feature volume to fully exploit spatial and spatial-spectral features. Driven by the goal of extracting and exploiting the best possible features, Alipour et al [15] and Roy et al [16] explored new architectural designs to make the convolutional kernel more flexible.…”

Section: Introductionmentioning

confidence: 99%

Morphological Convolutional Neural Networks for Hyperspectral Image Classification

Roy¹,

Mondal

Paoletti

et al. 2021

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

Self Cite

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) have become quite popular for solving many different tasks in remote sensing data processing. The convolution is a linear operation which extracts features from the input data. However, nonlinear operations are able to better characterize the internal relationships and hidden patterns within complex remote sensing data, such as hyperspectral images (HSIs). Morphological operations are powerful nonlinear transformations for feature extraction that preserve the essential characteristics of the image, such as borders, shape and structural information. In this paper, a new end-to-end morphological deep learning framework (called MorphConvHyperNet) is introduced. The proposed approach efficiently models nonlinear information during the training process of HSI classification. Specifically our method includes spectral and spatial morphological blocks to extract relevant features from the HSI input data. These morphological blocks consist of two basic 2D morphological operators (erosion and dilation) in the respective layers, followed by a weighted combination of the feature maps. Both layers can successfully encode the nonlinear information related to shape and size, playing an important role in classification performance. Our experimental results, obtained on five widely used HSIs, reveal that our newly proposed MorphConvHyperNet offers comparable (and even superior) performance when compared to traditional 2D and 3D

show abstract

Section: Introductionmentioning

confidence: 99%

Morphological Convolutional Neural Networks for Hyperspectral Image Classification

Roy¹,

Mondal

Paoletti

et al. 2021

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

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to verify the classification accuracy and real-time performance of the proposed ACAS2F2N, this paper compares the performance of 7 baselines. The specific description is as follows: A2S2KResNet 4 (TGRS, 2020), DBDA 13 (RS, 2020), PyResNet 18 (TGRS2019), DBMA 76 (RS, 2019), SSRN 14 (TGRS, 2018), FDSSC 15 (RS, 2018), ContextNet 17 (TIP, 2017).…”

Section: Resultsmentioning

confidence: 99%

“…Figures 5 , 6 and 7 are the results of algorithm classification maps, which respectively illustrate the results of hyperspectral classification and classification color labels. The experiment selects 7 baseline algorithms for performance comparison, of which 7 baselines are A2S2KResNet 4 (TGRS, 2020), DBDA 13 (RS, 2020), PyResNet 18 (TGRS2019), DBMA 76 (RS, 2019), SSRN 14 (TGRS, 2018), FDSSC 15 (RS, 2018), and ContextNet 17 (TIP, 2017). Experimental results verify the effectiveness and real-time performance of the proposed ACAS2F2N.…”

Section: Resultsmentioning

confidence: 99%

“…Tang et al 3 introduced octave convolution to capture features with strong discriminative ability. Tang et al 4 developed an improved residual network, which has a spectral-spatial kernel function and receptive field of different scales (A2S2K-ResNet). Xu et al 5 studied the fully convolutional network based on dense conditional random fields and atrous convolution to deal with hyperspectral classification.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

“…Compare with different methodsIn order to evaluate the performance of our proposed method MSDBFA, we select eight classification methods to compare with our model. The eight methods are support vector machine (SVM) with radial basis function kernel, multinomial logistic regression (MLR), random forest (RF), spectral CNN (CNN-1D), spatial CNN with 2-D kernels, Hybrid-SN[55], SSRN[40], A2S2KResnet[56]. Among them, SVM, RF and MLR are classical machine learning classification methods.…”

mentioning

confidence: 99%

A Multiscale Dual-Branch Feature Fusion and Attention Network for Hyperspectral Images Classification

Zhang

Chen

2021

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

View full text Add to dashboard Cite

Recently, hyperspectral image classification based on deep learning has achieved considerable attention. Many CNN classification methods have emerged and exhibited superior classification performance. However, most methods focus on extracting features by using fixed convolution kernels and layer-wise representation, resulting in feature extraction singleness. Additionally, the feature fusion process is rough and simple. Numerous methods get accustomed to fusing different levels of features by stacking modules hierarchically, which ignore the combination of shallow and deep spectral-spatial features. In order to overcome the preceding issues, a novel multiscale dual-branch feature fusion and attention network (MSDBFA) is proposed. Specifically, we design a multiscale feature extraction module (MSFE) to extract spatial-spectral features at a granular level and expand the range of receptive fields, thereby enhancing the multiscale feature extraction ability. Subsequently, we develop a dual-branch feature fusion interactive module (DBFM) that integrates the residual connection's feature reuse property and the dense connection's feature exploration capability, obtaining more discriminative features in both spatial and spectral branches. Additionally, we introduce a novel shuffle attention mechanism that allows for adaptive weighting of spatial and spectral features, further improving classification performance. Experimental results on three benchmark datasets demonstrate that our model outperforms other state-of-the-art methods while incurring the lower computational cost.

show abstract

Attention-Based Adaptive Spectral–Spatial Kernel ResNet for Hyperspectral Image Classification

Cited by 315 publications

References 62 publications

Morphological Convolutional Neural Networks for Hyperspectral Image Classification

Morphological Convolutional Neural Networks for Hyperspectral Image Classification

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

A Multiscale Dual-Branch Feature Fusion and Attention Network for Hyperspectral Images Classification

Contact Info

Product

Resources

About