FPGA: Fast Patch-Free Global Learning Framework for Fully End-to-End Hyperspectral Image Classification

Zheng, Zhuo; Zhong, Yanfei; Ma, Ailong; Zhang, Liangpei

doi:10.1109/tgrs.2020.2967821

Cited by 167 publications

(49 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Subsequently, this method has been widely used to obtain surface quantitative information [3]- [9]. Particularly, conducting land cover classification in complex geographical scenarios is advantageous owing to its rich spectral information [10], [11]. However, in complicated environments with substantial amounts of data and spatial structures resulting from multiple bands, the automatic classification of land cover using hyperspectral remote sensing images remains a challenging task owing to the number of details on surface elements, complex spectral characteristics of surface objects, high dimensionality of the spectral bands, and limited training samples [12]- [16].In the early stages of hyperspectral image classification research, most methods aim to utilize its spectral features during classification [17], including the K-nearest neighbor (KNN) [18], spectral angle [19], extreme learning machine (ELM) [20], and support vector machine (SVM) [21], [22].…”

Section: Introductionmentioning

confidence: 99%

“…However, these methods ignore inter-pixel spatial information [23], which limits any improvements to the classification accuracy. Spatial features are effective at improving the hyperspectral data representation and classification accuracy [10], [14], [24]- [28]. Although spatial features achieve optimal results for improving the classification accuracy, their performance is poor under conditions with limited samples.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

JAGAN: A Framework for Complex Land Cover Classification Using Gaofen-5 AHSI Images

Chen

Ouyang

Yang

et al. 2022

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

View full text Add to dashboard Cite

Owing to their powerful feature extraction capabilities, deep learning-based methods have achieved significant progress in hyperspectral remote sensing classification. However, several issues still exist in these methods, including a lack of hyperspectral datasets for specific complicated scenarios and the need to improve the classification accuracy of land cover with limited samples. Thus, to highlight and distinguish effective features, we propose a hyperspectral classification framework based on a joint channel-space attention mechanism and generative adversarial network (JAGAN). To relearn featurebased weights, a higher priority was assigned to important features, which was developed by integrating a two-joint channelspace attention model to obtain the most valuable feature via the attention weight map. Additionally, two classifiers were designed in JAGAN: sigmoid was used to determine whether the input data were real or fake samples produced by the generator, while Softmax was adopted as a land cover classifier to yield the prediction type labels of the input samples. To test the classification performance of the JAGAN model, we used a selfconstructed complex land cover dataset based on GaoFen-5 AHSI images, which consists of mixed landscapes of mining and agricultural areas from the urban-rural fringe. Compared with other methods, the proposed model achieved the highest overall classification accuracy of 86.09%, the highest kappa amount of 79.41%, the highest F1 score of 85.86%, and the highest average accuracy of 82.30%, indicating the JAGAN can effectively improve the classification accuracy for limited samples in complex regional environments using GF-5 AHSI images.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

JAGAN: A Framework for Complex Land Cover Classification Using Gaofen-5 AHSI Images

Chen

Ouyang

Yang

et al. 2022

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

View full text Add to dashboard Cite

show abstract

“…For example, 3-D CNN with 3-D convolutional kernels (e.g., 3 × 3 × 3) is employed for spectral-spatial feature extraction of HSI [39]. More recently, the fully convolutional network (FCN) is proposed for classification, which allows a whole HSI as input to the network without patch-based processing (i.e., extracting neighboring regions for each pixel) of HSI [40], [41]. Correspondingly, the output of FCN is a per-pixel classification map.…”

Section: Introductionmentioning

confidence: 99%

Efficient Deep Learning of Nonlocal Features for Hyperspectral Image Classification

Shen

Zhu

Chen

et al. 2021

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Deep learning based methods, such as Convolution Neural Network (CNN), have demonstrated their efficiency in hyperspectral image (HSI) classification. These methods can automatically learn spectral-spatial discriminative features within local patches. However, for each pixel in an HSI, it is not only related to its nearby pixels but also has connections to pixels far away from itself. Therefore, to incorporate the longrange contextual information, a deep fully convolutional network (FCN) with an efficient non-local module, named ENL-FCN, is proposed for HSI classification. In the proposed framework, a deep FCN considers an entire HSI as input and extracts spectralspatial information in a local receptive field. The efficient nonlocal module is embedded in the network as a learning unit to capture the long-range contextual information. Different from the traditional non-local neural networks, the long-range contextual information is extracted in a specially designed criss-cross path for computation efficiency. Furthermore, by using a recurrent operation, each pixel's response is aggregated from all pixels of HSI. The benefits of our proposed ENL-FCN are threefold: 1) the long-range contextual information is incorporated effectively, 2) the efficient module can be freely embedded in a deep neural network in a plug-and-play fashion, and 3) it has much fewer learning parameters and requires less computational resources. The experiments conducted on three popular HSI datasets demonstrate that the proposed method achieves state-of-theart classification performance with lower computational cost in comparison with several leading deep neural networks for HSI.

show abstract

“…In [19], a multi-scale spectral-spatial CNN (HyMSCN) was proposed to expand the receptive field and extract multi-scale spatial features by dilated convolutions of different sizes. Zheng et al presented a fast patch-free global learning framework (FPGA), which contains an encode-decoder-based FCN and adopts a global random hierarchical sampling (GS2) strategy to ensure fast and stable convergence [20]. To solve the sample problem of insufficiency and imbalance, Zhu et al designed a spectralspatial dependent global learning (SSDGL) framework based on FPAG [21].…”

Section: Introductionmentioning

confidence: 99%

From Local to Global: Class Feature Fused Fully Convolutional Network for Hyperspectral Image Classification

Liu

Jia

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Current mainstream networks for hyperspectral image (HSI) classification employ image patches as inputs for feature extraction. Spatial information extraction is limited by the size of inputs, which makes networks unable to perform effective learning and reasoning from the global perspective. As a common component for capturing long-range dependencies, non-local networks with pixel-by-pixel information interaction bring unaffordable computational costs and information redundancy. To address the above issues, we propose a class feature fused fully convolutional network (CFF-FCN) with a local feature extraction block (LFEB) and a class feature fusion block (CFFB) to jointly utilize local and global information. LFEB based on dilated convolutions and reverse loop mechanism can acquire the local spectral–spatial features at multiple levels and deliver shallower layer features for coarse classification. CFFB calculates global class representation to enhance pixel features. Robust global information is propagated to every pixel with low computational cost. CFF-FCN considers a fully global class context and obtains more discriminative representation by concatenating high-level local features and re-integrated global features. Experimental results conducted on three real HSI data sets demonstrate that the proposed fully convolutional network is superior to multiple state-of-the-art deep learning-based approaches, especially in the case of a small number of training samples.

show abstract

FPGA: Fast Patch-Free Global Learning Framework for Fully End-to-End Hyperspectral Image Classification

Cited by 167 publications

References 48 publications

JAGAN: A Framework for Complex Land Cover Classification Using Gaofen-5 AHSI Images

JAGAN: A Framework for Complex Land Cover Classification Using Gaofen-5 AHSI Images

Efficient Deep Learning of Nonlocal Features for Hyperspectral Image Classification

From Local to Global: Class Feature Fused Fully Convolutional Network for Hyperspectral Image Classification

Contact Info

Product

Resources

About