Hyperspectral Image Classification With Multi-Attention Transformer and Adaptive Superpixel Segmentation-Based Active Learning
The DOI matches its Crossref record; 61 of the 61 references it cites were found in a registry or an index.
Abstract
Deep learning (DL) based methods represented by convolutional neural networks (CNNs) are widely used in hyperspectral image classification (HSIC). Some of these methods have strong ability to extract local information, but the extraction of long-range features is slightly inefficient, while others are just the opposite. For example, limited by the receptive fields, CNN is difficult to capture the contextual spectral-spatial features from a long-range spectral-spatial relationship. Besides, the success of DL-based methods is greatly attributed to numerous labeled samples, whose acquisition are time-consuming and cost-consuming. To resolve these problems, a hyperspectral classification framework based on multi-attention Transformer (MAT) and adaptive superpixel segmentation-based active learning (MAT-ASSAL) is proposed, which successfully achieves excellent classification performance, especially under the condition of small-size samples. Firstly, a multi-attention Transformer network is built for HSIC. Specifically, the self-attention module of Transformer is applied to model long-range contextual dependency between spectral-spatial embedding. Moreover, in order to capture local features, an outlook-attention module which can efficiently encode fine-level features and contexts into tokens is utilized to improve the correlation between the center spectral-spatial embedding and its surroundings. Secondly, aiming to train a excellent MAT model through limited labeled samples, a novel active learning (AL) based on superpixel segmentation is proposed to select important samples for MAT. Finally, to better integrate local spatial similarity into active learning, an adaptive superpixel (SP) segmentation algorithm, which can save SPs in uninformative regions and preserve edge details in complex regions, is employed to generate better local spatial constraints for AL. Quantitative and qualitative results indicate that the MAT-ASSAL outperforms seven state-of-the-art methods on three HSI datasets.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
Classification of hyperspectral remote sensing images with support vector machines
Melgani, F., & Bruzzone, L. (2004) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2004.831865 · Cited by 4,411 · cited 7×
“Consequently, although the classification accuracy of SVM is low, SVM retains the clear edge of an HSI due to the reason that SVM can process each pixel of hyperspectral image directly.”
BackgroundMethodInfluentialHaboudane, D. (2004) · Remote Sensing of Environment · doi:10.1016/j.rse.2003.12.013 · Cited by 2,608 · cited 1×
“…[4], a hot research field which assigns each pixel with predefined labels by using some manually labeled samples [5], is widely used in agriculture [6], ecological monitoring [7], national defense [8], urban construction [9], and et al. Initially, the traditional machine learning (ML) methods that…”
BackgroundZhong, Z., Li, J., Luo, Z., & Chapman, M. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2017.2755542 · Cited by 1,959 · cited 7×
“In general, DBDA and A 2 S 2 K-ResNet can achieve good performance, but in some complex regions, such as the right region of houston, their results are not satisfactory.”
MethodInfluentialHybridSN: Exploring 3-D–2-D CNN Feature Hierarchy for Hyperspectral Image Classification
Roy, S. K., Krishna, G., Dubey, S. R., & Chaudhuri, B. B. (2020) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2019.2918719 · Cited by 1,898
Harsanyi, J. C., & Chang, C.-I. (1994) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/36.298007 · Cited by 1,517 · cited 1×
“In recent years, HSI classification (HSIC) [3], [4], a hot research field which assigns each pixel with predefined labels by using some manually labeled samples [5], is widely used in agriculture [6], ecological monitoring [7], national defense [8], urban construction [9], and et al. Initially, the…”
BackgroundSpectralFormer: Rethinking Hyperspectral Image Classification With Transformers
Hong, D., Han, Z., Yao, J., Gao, L., Zhang, B., Plaza, A., & Chanussot, J. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3130716 · Cited by 1,382 · cited 2×
“Motivated by ViT, a SpectralFormer [33] which splits the spectral bands of HSIs into multiple groups (tokens) is proposed for HSIC.”
BackgroundGoing deeper with Image Transformers
Touvron, H., Cord, M., Sablayrolles, A., Synnaeve, G., & Jegou, H. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00010 · Cited by 1,259 · cited 2×
“The goal of Cl_A [64] is to avoid conflicts that may arise from inconsistent learning objectives between patch embeddings and the class token, so the Cl_A freezes patch embeddings and only updates the class token.”
BackgroundMethodSpectral and Spatial Classification of Hyperspectral Data Using SVMs and Morphological Profiles
Fauvel, M., Benediktsson, J. A., Chanussot, J., & Sveinsson, J. R. (2008) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2008.922034 · Cited by 990 · cited 1×
“[3], [4], a hot research field which assigns each pixel with”
Background3-D Deep Learning Approach for Remote Sensing Image Classification
Ben Hamida, A., Benoit, A., Lambert, P., & Ben Amar, C. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2818945 · Cited by 875
Collaborative representation for hyperspectral anomaly detection
Li, W., & Du, Q. (2015) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2014.2343955 · Cited by 758 · cited 2×
“The candidate interval of h and p are set to [12:4:32] and [2:2:8], respectively.”
BackgroundSelf-citationDeep Learning for Classification of Hyperspectral Data: A Comparative Review
Audebert, N., Le Saux, B., & Lefevre, S. (2019) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2019.2912563 · Cited by 686 · cited 1×
“training [67], [68], which may result in overfitting to the dataset and learning a shortcut solution.”
BackgroundZhong, Y., Hu, X., Luo, C., Wang, X., Zhao, J., & Zhang, L. (2020) · Remote Sensing of Environment · doi:10.1016/j.rse.2020.112012 · Cited by 596 · cited 1×
“With the rise of deep learning (DL), a large number of DL-based methods are used to tackle hyperspectral image classification tasks [12],”
MethodRasti, B., Hong, D., Hang, R., Ghamisi, P., Kang, X., Chanussot, J., & Benediktsson, J. A. (2020) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2020.2979764 · Cited by 537 · cited 1×
“With the rise of deep learning (DL), a large number of DL-based methods are used to tackle hyperspectral image classification tasks [12], [13].”
MethodClassification of Hyperspectral Image Based on Double-Branch Dual-Attention Mechanism Network
Li, R., Zheng, S., Duan, C., Yang, Y., & Wang, X. (2020) · Remote Sensing · doi:10.3390/rs12030582 · Cited by 519
Attention-Based Adaptive Spectral–Spatial Kernel ResNet for Hyperspectral Image Classification
Roy, S. K., Manna, S., Song, T., & Bruzzone, L. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3043267 · Cited by 519 · cited 2×
“…several representative methods belong to different categories with different advantages are selected to compare with the proposed framework MAT-ASSAL, which are SVM [10], 3D-CNN [15], SGL [51], SSAL-SN [58], FAAL [65], HSI-BERT [31], DBDA [66], HybridSN [16] and A 2 S 2 K-ResNet [28].”
MethodSemi-Supervised Deep Learning Using Pseudo Labels for Hyperspectral Image Classification
Wu, H., & Prasad, S. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2772836 · Cited by 463 · cited 2×
“semi-supervised methods [36] are used to alleviate the HSIC problem of low classification accuracy under the condition of small sample size.”
MethodLiu, Q., Xiao, L., Yang, J., & Wei, Z. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3037361 · Cited by 440 · cited 1×
“[50] constructed a hyperspectral GCN model to extract the superpixel-wise spatial feature and then used CNN’s local information to generate complementary spectral-spatial features at the pixel and”
MethodHe, J., Zhao, L., Yang, H., Zhang, M., & Li, W. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2934760 · Cited by 383 · cited 6×
“[31] first proposed a HSIC framework based on the encoder of Transformer, named HSI-BERT, which employed the dynamic input regions to jointly train Transformer.”
MethodInfluentialSelf-citationFang, L., Li, S., Duan, W., Ren, J., & Benediktsson, J. A. (2015) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2015.2445767 · Cited by 371 · cited 1×
“spatial-adaptive regions with similar spectral features [44].”
Hyperspectral Image Classification With Convolutional Neural Network and Active Learning
Cao, X., Yao, J., Xu, Z., & Meng, D. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2964627 · Cited by 365 · cited 1×
“[42] combined AL and CNN to reduce the number of labeled samples required for training.”
BackgroundSpectral–Spatial Hyperspectral Image Classification via Multiscale Adaptive Sparse Representation
Fang, L., Li, S., Kang, X., & Benediktsson, J. A. (2014) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2014.2318058 · Cited by 321 · cited 1×
“representation [11] were applied in HSIC, but these ML-based”
MethodSpectral-Spatial Unified Networks for Hyperspectral Image Classification
Xu, Y., Zhang, L., Du, B., & Zhang, F. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2827407 · Cited by 316 · cited 1×
“kernel to extract spatial features was proposed by [14].”
BackgroundVOLO: Vision Outlooker for Visual Recognition
Yuan, L., Hou, Q., Jiang, Z., Feng, J., & Yan, S. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3206108 · Cited by 288 · cited 2×
“Besides, the outlook attention [62] which can efficiently encode finer-level features and contexts into tokens is utilized to improve the correlation between the center token and surroundings.”
MethodHaut, J. M., Paoletti, M. E., Plaza, J., Li, J., & Plaza, A. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2838665 · Cited by 288 · cited 1×
“In order to obtain a excellent model and save the cost of manual labeling, active learning (AL) strategy, which selects important training samples for the classifier according to the prediction of model, is used in HSIC [37], [38], [39], [40].”
MethodFeature Extraction With Multiscale Covariance Maps for Hyperspectral Image Classification
He, N., Paoletti, M. E., Haut, J. M., Fang, L., Li, S., Plaza, A., & Plaza, J. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2860464 · Cited by 270 · cited 1×
“predefined labels by using some manually labeled samples [5],”
BackgroundZhong, Z., Li, Y., Ma, L., Li, J., & Zheng, W.-S. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3115699 · Cited by 241 · cited 1×
“network (SSTN) is proposed in [32], which consists of spatial”
BackgroundZheng, Z., Zhong, Y., Ma, A., & Zhang, L. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2967821 · Cited by 218 · cited 1×
“[19] first proposed the new global stochastic stratified sampling strategy and patch-free global learning”
BackgroundRemote sensing monitoring of multi-scale watersheds impermeability for urban hydrological evaluation
Shao, Z., Fu, H., Li, D., Altan, O., & Cheng, T. (2019) · Remote Sensing of Environment · doi:10.1016/j.rse.2019.111338 · Cited by 209 · cited 1×
“…by using some manually labeled samples [5], is widely used in agriculture [6], ecological monitoring [7], national defense [8], urban construction [9], and et al. Initially, the traditional machine learning (ML) methods that only take the spectral information into consideration such as support…”
MethodA Supervised Segmentation Network for Hyperspectral Image Classification
Sun, H., Zheng, X., & Lu, X. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3055613 · Cited by 205 · cited 1×
“pseudo-labels to augment training samples [52], [53] or combining superpixel segmentation into representation learning to”
BackgroundMulti-Scale Dense Networks for Hyperspectral Remote Sensing Image Classification
Zhang, C., Li, G., & Du, S. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2925615 · Cited by 202 · cited 2×
“connection, such as ResNet [21] and DenseNet [22], was utilized in HSIC.”
MethodHyperspectral Image Denoising Using a 3-D Attention Denoising Network
Shi, Q., Tang, X., Yang, T., Liu, R., & Zhang, L. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3045273 · Cited by 201 · cited 1×
“were applied in HSIC, such as 3D attention networks [24],”
MethodZhu, Q., Deng, W., Zheng, Z., Zhong, Y., Guan, Q., Lin, W., Zhang, L., & Li, D. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3070577 · Cited by 190 · cited 1×
“[20] proposed a spectral-spatialdependent global learning framework for insufficient and imbalanced HSIC.”
BackgroundFeedback Attention-Based Dense CNN for Hyperspectral Image Classification
Yu, C., Han, R., Song, M., Liu, C., & Chang, C. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3058549 · Cited by 180 · cited 1×
“…modules were applied in HSIC, such as 3D attention networks [24], hierarchical homogeneity-attention network [25], attention-based dense CNN [26], attention-based second-order pooling network [27], attention-based adaptive spectral–spatial kernel ResNet [28] and spatial-spectral…”
MethodAlmeida, D. R. A. D., Broadbent, E. N., Ferreira, M. P., Meli, P., Zambrano, A. M. A., Gorgens, E. B., Resende, A. F., de Almeida, C. T., do Amaral, C. H., Corte, A. P. D., et al. (2021) · Remote Sensing of Environment · doi:10.1016/j.rse.2021.112582 · Cited by 179 · cited 1×
“…assigns each pixel with predefined labels by using some manually labeled samples [5], is widely used in agriculture [6], ecological monitoring [7], national defense [8], urban construction [9], and et al. Initially, the traditional machine learning (ML) methods that only take the spectral…”
BackgroundXu, Y., Du, B., & Zhang, L. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3118977 · Cited by 162 · cited 1×
“quantity and quality of training samples [34].”
Liang, J., Zhou, J., Qian, Y., Wen, L., Bai, X., & Gao, Y. (2016) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2016.2616489 · Cited by 150 · cited 1×
“However, since there may be potential overlap between the training and testing datasets, the model will implicitly utilize or observe the testing distribution during training [67], [68], which may result in overfitting to the dataset and learning a shortcut solution.”
Deep Multiview Learning for Hyperspectral Image Classification
Liu, B., Yu, A., Yu, X., Wang, R., Gao, K., & Guo, W. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3034133 · Cited by 144 · cited 1×
“HSIC task is expensive and time-consuming [35].”
Extended Random Walker-Based Classification of Hyperspectral Images
Kang, X., Shutao Li, A., Fang, L., Li, M., & Benediktsson, J. A. (2014) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2014.2319373 · Cited by 122 · cited 1×
“national defense [8], urban construction [9], and et al.”
BackgroundSuperpixel Contracted Graph-Based Learning for Hyperspectral Image Classification
Sellars, P., Avilés-Rivero, A. I., & Schönlieb, C. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2961599 · Cited by 104 · cited 11×
“Compared with the supervised-based methods, the semi-supervised SGL can achieve high accuracy, but its’ classification performance is limited when the sample is relatively sufficient (i.e., YRE).”
BackgroundMethodInfluentialZhang, H., Zou, J., & Zhang, L. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3163326 · Cited by 99 · cited 1×
“[46] or graph convolutional networks (GCNs) [47], [48], [49].”
BackgroundAttention-Based Second-Order Pooling Network for Hyperspectral Image Classification
Xue, Z., Zhang, M., Liu, Y., & Du, P. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3048128 · Cited by 93 · cited 1×
“network [27], attention-based adaptive spectral–spatial kernel”
Jia, S., Deng, X., Zhu, J., Xu, M., Zhou, J. W., & Jia, X. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2916329 · Cited by 85 · cited 1×
“constrain pixels in homogeneous regions [54], [55].”
Self-citationActive Learning With Gaussian Process Classifier for Hyperspectral Image Classification
Sun, S., Zhong, P., Xiao, H., & Wang, R. (2014) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2014.2347343 · Cited by 84 · cited 1×
“Sun et al. proposed an AL method combined with the Gaussian process classifier for HSIC [41].”
MethodLi, J., Du, Q., Li, Y., & Li, W. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2813366 · Cited by 63 · cited 1×
“ResNet [28] and spatial-spectral self-attention network [29].”
Self-citationBayesian Adaptive Superpixel Segmentation
Uziel, R., Ronen, M., & Freifeld, O. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00856 · Cited by 58 · cited 3×
“Assuming that the initial number of superpixels is K 0 , different from K 0 in paper [63] which is a fixed value, the setting of K 0 in this paper is related to the spatial prior of hyperspectral images.”
BackgroundMethodInfluentialSuperpixel-Guided Discriminative Low-Rank Representation of Hyperspectral Images for Classification
Yang, S., Hou, J., Jia, Y., Mei, S., & Du, Q. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3120675 · Cited by 46 · cited 1×
“[57] achieved superpixel-guided discriminative low-rank representation by using classification-guided superpixel segmentation to group homogeneous pixels into clusters and then feeding them into their novel discriminative low-rank representation.”
MethodSuperpixel-Level Weighted Label Propagation for Hyperspectral Image Classification
Jia, S., Deng, X., Xu, M., Zhou, J. W., & Jia, X. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2972294 · Cited by 42 · cited 1×
“[46] or graph convolutional networks (GCNs) [47], [48], [49].”
BackgroundSelf-citationZhang, Z., Pasolli, E., & Crawford, M. M. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2952319 · Cited by 41
Hyperspectral Image Classification with Feature-Oriented Adversarial Active Learning
Wang, G., & Ren, P. (2020) · Remote Sensing · doi:10.3390/rs12233879 · Cited by 38 · cited 1×
“…several representative methods belong to different categories with different advantages are selected to compare with the proposed framework MAT-ASSAL, which are SVM [10], 3D-CNN [15], SGL [51], SSAL-SN [58], FAAL [65], HSI-BERT [31], DBDA [66], HybridSN [16] and A 2 S 2 K-ResNet [28].”
MethodMultiview Spatial–Spectral Active Learning for Hyperspectral Image Classification
Xu, M., Zhao, Q., & Jia, S. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3095292 · Cited by 36 · cited 1×
“In order to obtain a excellent model and save the cost of manual labeling, active learning (AL) strategy, which selects important training samples for the classifier according to the prediction of model, is used in HSIC [37], [38], [39], [40].”
MethodA Blind Multiscale Spatial Regularization Framework for Kernel-Based Spectral Unmixing
Borsoi, R. A., Imbiriba, T., Bermudez, J. C. M., & Richard, C. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2978342 · Cited by 34
Ma, K. Y., & Chang, C. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3053204 · Cited by 28 · cited 1×
“In order to obtain a excellent model and save the cost of manual labeling, active learning (AL) strategy, which selects important training samples for the classifier according to the prediction of model, is used in HSIC [37], [38], [39], [40].”
MethodGong, Z., Tong, L., Zhou, J. W., Qian, B., Duan, L., & Xiao, C. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3198931 · Cited by 24 · cited 1×
“[46] or graph convolutional networks (GCNs) [47], [48], [49].”
BackgroundXu, H., Zhang, H., & Zhang, L. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3040879 · Cited by 24 · cited 1×
“pseudo-labels to augment training samples [52], [53] or combining superpixel segmentation into representation learning to”
BackgroundWide Contextual Residual Network with Active Learning for Remote Sensing Image Classification
Liu, S. K., Luo, H., Tu, Y., He, Z., & Li, J. (2018) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2018.8517855 · Cited by 21 · cited 1×
“[43] employed the AL to train a deep contextual residual network for HSIC.”
MethodZhao, C., Zhu, W., & Feng, S. (2021) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2021.3084203 · Cited by 20 · cited 1×
“[17] proposed a method based on kernel-guide deformable convolution and double-window joint bilateral filter.”
MethodSelf-citationSemi-Supervised Superpixel-Based Multi-Feature Graph Learning for Hyperspectral Image Data
Kotzagiannidis, M. S., & Schönlieb, C. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3112298 · Cited by 20 · cited 1×
“A line of works aims to utilize the superpixel segmentation mainly for graph-based learning [45], [46] or graph convolutional networks (GCNs) [47], [48], [49].”
BackgroundH2AN: Hierarchical Homogeneity-Attention Network for Hyperspectral Image Classification
Li, S., Luo, X., Wang, Q., Li, L., & Yin, J. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3086841 · Cited by 19 · cited 1×
“hierarchical homogeneity-attention network [25], attention-”
Su, H., Gao, Y., & Du, Q. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3161139 · Cited by 11 · cited 1×
“constrain pixels in homogeneous regions [54], [55].”
Cited by
Tracing unknown tumor origins with a biological-pathway-based transformer model
Xie, J., Chen, Y., Luo, S., Yang, W., Lin, Y., Wang, L., Ding, X., Tong, M., & Yu, R. (2024) · Cell Reports Methods · doi:10.1016/j.crmeth.2024.100797 · Cited by 9
Metadata
- Authors
- Zhao, C., Qin, B., Feng, S., Zhu, W., Sun, W., Li, W., & Jia, X.
- Venue
- IEEE Transactions on Image Processing
- Published
- 2023
- Volume
- 32
- Pages
- 3606-3621
- ISSN
- 1057-7149 (ISSN-L)
- 1941-0042
- OpenAlex
- W4382203304
- Cited by
- 190
- References
- 61
- FWCI
- 20.98
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.