FPGA: Fast Patch-Free Global Learning Framework for Fully End-to-End Hyperspectral Image Classification
Open accessThe DOI matches its Crossref record; 50 of the 50 references it cites were found in a registry or an index.
Abstract
Deep learning techniques have provided significant improvements in hyperspectral image (HSI) classification. The current deep learning-based HSI classifiers follow a patch-based learning framework by dividing the image into overlapping patches. As such, these methods are local learning methods, which have a high computational cost. In this article, a fast patch-free global learning (FPGA) framework is proposed for HSI classification. The proposed framework consists of three main parts: 1) a designed sampling strategy; 2) an encoder-decoder-based fully convolutional network (FCN); and 3) lateral connections between the encoder and decoder. In FPGA, an encoder-decoder-based FCN is utilized to consider the global spatial information by processing the whole image, which results in fast inference. However, it is difficult to directly utilize the encoder-decoder-based FCN for HSI classification as it always fails to converge due to the insufficiently diverse gradients caused by the limited training samples. To solve the divergence problem and maintain the FCNs abilities of fast inference and global spatial information mining, a global stochastic stratified (GS2) sampling strategy is first proposed by transforming all the training samples into a stochastic sequence of stratified samples. This strategy can obtain diverse gradients to guarantee the convergence of the FCN in the FPGA framework. For a better design of FCN architecture, FreeNet, which is a fully end-to-end network for HSI classification, is proposed to maximize the exploitation of the global spatial information and boost the performance via a spectral attention-based encoder and a lightweight decoder. A lateral connection module is also designed to connect the encoder and decoder, fusing the spatial details in the encoder and the semantic features in the decoder. The experimental results obtained using three public benchmark data sets suggest that the FPGA framework is superior to the patch-based framework in both speed and accuracy for HSI classification.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“The design of the lateral connection-based SSF follows that of residual learning [50].”
BackgroundLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
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
Squeeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2016) · arXiv · doi:10.48550/arxiv.1606.00915 · Cited by 22,392
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2699184 · Cited by 22,392 · cited 1×
“The model architecture follows the classical encoder–decoder framework [42], [44]–[46] with semantic-spatial fusion (SSF).”
MethodSegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2644615 · Cited by 19,631
Squeeze-and-Excitation Networks
Hu, J., Shen, L., Albanie, S., Sun, G., & Wu, E. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2913372 · Cited by 12,157
Fully convolutional networks for semantic segmentation
Shelhamer, E., Long, J., & Darrell, T. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2572683 · Cited by 11,898
A Stochastic Approximation Method
Robbins, H., & Monro, S. (1951) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177729586 · Cited by 9,643 · cited 3×
“Stochastic gradient descent (SGD) [47] is used to minimize the classification loss l (e.g., cross-entropy loss) over the sampled positions R.”
MethodInfluentialClassification 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 8×
“CLASSIFICATION RESULTS OF SVM [8], S-CNN [38], GABOR-CNN [39], DFFN [40], 3-D-GAN [51] AND FREENET ON THE SALINAS DATA SET”
MethodInfluentialWu, Y., & He, K. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01198-w · Cited by 3,601 · cited 1×
“module of the encoder network is a 3 × 3 convolutional layer followed by group normalization [48] and rectified linear unit (ReLU) activation.”
Chen, Y., Jiang, H., Li, C., Jia, X., & Ghamisi, P. (2016) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2016.2584107 · Cited by 2,984 · cited 1×
“The deep networks include stacked autoencoders (SAEs), deep belief networks (DBNs), CNNs, recurrent neural networks (RNNs), and generative adversarial networks (GANs), which have all been explored in HSI classification [22], [23], [26], [27], [31]–[35].”
BackgroundDeep learning-based classification of hyperspectral data
Chen, Y., Lin, Z., Zhao, X., Wang, G., & Gu, Y. (2014) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2014.2329330 · Cited by 2,679 · cited 3×
“These CNNbased methods follow a patch-based local learning framework [22, 23, 25, 29–32], where patch generation is first performed to obtain a dense set of patches with a fixed size S × S and then patchwise classification is applied to each patch.”
BackgroundMethodRandom Forests for land cover classification
Gislason, P. O., Benediktsson, J. A., & Sveinsson, J. R. (2006) · Pattern Recognition Letters · doi:10.1016/j.patrec.2005.08.011 · Cited by 2,244 · cited 1×
“For HSI classification, the spectral feature-based methods, such as support vector machine (SVM) [8], random forest (RF) [9], rotation forest (RoF) [10], canonical correlation forest (CCF) [11, 12] and multinomial logistic regression (MLR) [13], are the traditional classifiers for HSIs.”
MethodDeep Learning for Hyperspectral Image Classification: An Overview
Li, S., Song, W., Fang, L., Chen, Y., Ghamisi, P., & Benediktsson, J. A. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2907932 · Cited by 2,007 · cited 3×
“HYPERSPECTRAL imaging, as a particularly important technique, is able to obtain abundant spectral information about the ground surface [1]–[3].”
BackgroundMethodDeep Convolutional Neural Networks for Hyperspectral Image Classification
Hu, W., Huang, Y., Wei, L., Zhang, F., & Li, H. (2015) · Journal of Sensors · doi:10.1155/2015/258619 · Cited by 1,941 · cited 2×
“A simple deep CNN was employed for HSI classification in [26].”
BackgroundMethodClassification of hyperspectral data from urban areas based on extended morphological profiles
Benediktsson, J. A., Palmason, J. A., & Sveinsson, J. R. (2005) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2004.842478 · Cited by 1,393 · cited 1×
“Extended morphological profiles (EMPs) [20], [21] have also been proposed to leverage the spatial context with multiple morphological operations for HSI classification.”
BackgroundSpectral-spatial classification of hyperspectral data based on deep belief network
Chen, Y., Zhao, X., & Jia, X. (2015) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2015.2388577 · Cited by 1,259 · cited 1×
“The deep networks include stacked autoencoders (SAEs), deep belief networks (DBNs), CNNs, recurrent neural networks (RNNs) and generative adversarial networks (GANs), which have all been explored in HSI classification [22, 23, 26, 27, 31–35].”
BackgroundZhao, W., & Du, S. (2016) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2016.2543748 · Cited by 1,212 · cited 1×
“A spectral–spatial feature-based classification framework was proposed in [34], combining a balanced local discriminant embedding algorithm used as the spectral feature extractor with the CNN used as a spectral–spatial feature extractor for HSI classification.”
MethodAdam, E., Mutanga, O., & Rugege, D. (2010) · Wetlands Ecology and Management · doi:10.1007/s11273-009-9169-z · Cited by 1,018 · cited 1×
“As a result, it is widely applied in the fields of geology, agriculture, forestry, and environmental monitoring [4–6].”
BackgroundSpectral 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×
“To further improve the accuracy of HSI classification, spatial information has been integrated into the existing pipelines [14]–[16].”
MethodSparse multinomial logistic regression: fast algorithms and generalization bounds
Krishnapuram, B., Carin, L., Figueiredo, M. A. T., & Hartemink, A. J. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.127 · Cited by 877 · cited 1×
“For HSI classification, the spectral feature-based methods, such as support vector machine (SVM) [8], random forest (RF) [9], rotation forest (RoF) [10], canonical correlation forest (CCF) [11], [12], and multinomial logistic regression (MLR) [13], are the traditional classifiers for HSIs.”
MethodHyperspectral Image Classification Using Deep Pixel-Pair Features
Li, W., Wu, G., Zhang, F., & Du, Q. (2017) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2016.2616355 · Cited by 805 · cited 1×
“A CNN with pixel-pair features (CNN-PPF) was proposed in [37] to enhance the original CNN by using deep pixel-pair features.”
MethodAdvances in Hyperspectral Image Classification: Earth Monitoring with Statistical Learning Methods
Camps-Valls, G., Tuia, D., Bruzzone, L., & Benediktsson, J. A. (2014) · IEEE Signal Processing Magazine · doi:10.1109/msp.2013.2279179 · Cited by 781 · cited 1×
“Hyperspectral image (HSI) classification with the goal to assign a unique semantic label to each pixel in an HSI [7] is a fundamental but challenging part of hyperspectral remote sensing (HRS).”
BackgroundGenerative Adversarial Networks for Hyperspectral Image Classification
Zhu, L., Chen, Y., Ghamisi, P., & Benediktsson, J. A. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2805286 · Cited by 734 · cited 4×
“TABLE III THE CLASSIFICATION RESULTS OF SVM [8], S-CNN[38], GABOR-CNN [39], DFFN [40], 3D-GAN [51] AND FREENET ON THE ROSIS-03 PAVIA UNIVERSITY DATASET.”
MethodInfluentialConvolutional neural networks for hyperspectral image classification
Yu, S., Jia, S., & Xu, C. (2017) · Neurocomputing · doi:10.1016/j.neucom.2016.09.010 · Cited by 703 · cited 1×
“Among the deep learning based methods, convolutional neural networks (CNNs), as hierarchical spectral-spatial feature representation learning frameworks, have been widely used in HSI classification [25–29], significantly boosting the accuracy when compared with the traditional methods.”
MethodSpectral–Spatial Classification of Hyperspectral Imagery Based on Partitional Clustering Techniques
Tarabalka, Y., Benediktsson, J. A., & Chanussot, J. (2009) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2009.2016214 · Cited by 678 · cited 1×
“To further improve the accuracy of HSI classification, spatial information has been integrated into the existing pipelines [14–16].”
MethodA new deep convolutional neural network for fast hyperspectral image classification
Paoletti, M. E., Haut, J. M., Plaza, J., & Plaza, A. (2018) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2017.11.021 · Cited by 607 · cited 2×
“These CNN-based methods follow a patch-based local learning framework [22], [23], [25], [29]–[32], where patch generation is first performed to obtain a dense set of patches with a fixed”
MethodHyperspectral Image Classification With Deep Feature Fusion Network
Song, W., Li, S., Fang, L., & Lu, T. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2794326 · Cited by 574 · cited 5×
“CLASSIFICATION RESULTS OF SVM [8], S-CNN [38], GABOR-CNN [39], DFFN [40], 3-D-GAN [51] AND FREENET ON THE SALINAS DATA SET”
MethodInfluentialCascaded Recurrent Neural Networks for Hyperspectral Image Classification
Hang, R., Liu, Q., Hong, D., & Ghamisi, P. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2899129 · Cited by 534 · cited 1×
“These CNN-based methods follow a patch-based local learning framework [22], [23], [25], [29]–[32], where patch generation is first performed to obtain a dense set of patches with a fixed”
MethodSpectral–spatial classification of hyperspectral images using deep convolutional neural networks
Yue, J., Zhao, W., Mao, S., & Liu, H. (2015) · Remote Sensing Letters · doi:10.1080/2150704x.2015.1047045 · Cited by 525 · cited 2×
“These CNN-based methods follow a patch-based local learning framework [22], [23], [25], [29]–[32], where patch generation is first performed to obtain a dense set of patches with a fixed”
MethodGeneralized Composite Kernel Framework for Hyperspectral Image Classification
Li, J., Marpu, P. R., Plaza, A., Bioucas-Dias, J. M., & Benediktsson, J. A. (2013) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2012.2230268 · Cited by 484 · cited 1×
“Extended morphological profiles (EMPs) [20], [21] have also been proposed to leverage the spatial context with multiple morphological operations for HSI classification.”
BackgroundKoch, B. (2010) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2010.09.001 · Cited by 339 · cited 1×
“As a result, it is widely applied in fields such as geology, agriculture, forestry, and environmental monitoring [4]–[6].”
BackgroundLi, J., Bioucas-Dias, J. M., & Plaza, A. (2013) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2012.2205263 · Cited by 336
Ghamisi, P., Maggiori, E., Li, S., Souza, R., Tarablaka, Y., Moser, G., De Giorgi, A., Fang, L., Chen, Y., Chi, M., et al. (2018) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2018.2854840 · Cited by 325 · cited 2×
“HYPERSPECTRAL imaging, as a particularly important technique, is able to obtain abundant spectral information about the ground surface [1]–[3].”
BackgroundMethodMini-UAV-Borne Hyperspectral Remote Sensing: From Observation and Processing to Applications
Zhong, Y., Wang, X., Xu, Y., Wang, S., Jia, T., Hu, X., Zhao, J., Wei, L., & Zhang, L. (2018) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2018.2867592 · Cited by 318 · cited 1×
“cn) HYPERSPECTRAL imaging, as a particularly important technique, is able to obtain abundant spectral information about the ground surface [1–3].”
Self-citationSpectral-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 3×
“The deep networks include stacked autoencoders (SAEs), deep belief networks (DBNs), CNNs, recurrent neural networks (RNNs), and generative adversarial networks (GANs), which have all been explored in HSI classification [22], [23], [26], [27], [31]–[35].”
BackgroundMethodSelf-citationA Robust Built-Up Area Presence Index by Anisotropic Rotation-Invariant Textural Measure
Pesaresi, M., Gerhardinger, A., & Kayitakire, F. (2008) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2008.2002869 · Cited by 311 · cited 1×
“Thereby, spectral-spatial feature based methods, such as the gray level cooccurrence matrix [17], wavelet transform [18], the Gabor filter [19], etc.”
MethodLearning Compact and Discriminative Stacked Autoencoder for Hyperspectral Image Classification
Zhou, P., Han, J., Cheng, G., & Zhang, B. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2893180 · Cited by 289 · cited 1×
“The deep networks include stacked autoencoders (SAEs), deep belief networks (DBNs), CNNs, recurrent neural networks (RNNs), and generative adversarial networks (GANs), which have all been explored in HSI classification [22], [23], [26], [27], [31]–[35].”
BackgroundHyperspectral Images Classification With Gabor Filtering and Convolutional Neural Network
Chen, Y., Zhu, L., Ghamisi, P., Jia, X., Li, G., & Tang, L. (2017) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2017.2764915 · Cited by 270 · cited 5×
“CLASSIFICATION RESULTS OF SVM [8], S-CNN [38], GABOR-CNN [39], DFFN [40], 3-D-GAN [51] AND FREENET ON THE SALINAS DATA SET”
MethodInfluentialSupervised Deep Feature Extraction for Hyperspectral Image Classification
Liu, B., Yu, X., Zhang, P., Yu, A., Fu, Q., & Wei, X. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2017.2769673 · Cited by 265 · cited 5×
“CLASSIFICATION RESULTS OF SVM [8], S-CNN [38], GABOR-CNN [39], DFFN [40], 3-D-GAN [51] AND FREENET ON THE SALINAS DATA SET”
MethodInfluentialA CNN With Multiscale Convolution and Diversified Metric for Hyperspectral Image Classification
Gong, Z., Zhong, P., Yu, Y., Hu, W., & Li, S. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2886022 · Cited by 245 · cited 1×
“The deep networks include stacked autoencoders (SAEs), deep belief networks (DBNs), CNNs, recurrent neural networks (RNNs), and generative adversarial networks (GANs), which have all been explored in HSI classification [22], [23], [26], [27], [31]–[35].”
BackgroundDeformable Convolutional Neural Networks for Hyperspectral Image Classification
Zhu, J., Fang, L., & Ghamisi, P. (2018) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2018.2830403 · Cited by 244 · cited 1×
“The deformable HSI classification networks (DHCNet) method [30] uses an adaptive spatial context modeling method to capture the complex spatial context in the HSIs and boost the performance.”
MethodJiao, L., Liang, M., Chen, H., Yang, S., Liu, H., & Cao, X. (2017) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2017.2710079 · Cited by 217 · cited 1×
“Although the DMS3FE-classifier [41] utilizes a pretrained FCN [42] to extract features, its own FCN is not trained.”
MethodHyperspectral Remote Sensing Image Classification Based on Rotation Forest
Xia, J., Du, P., He, X., & Chanussot, J. (2014) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2013.2254108 · Cited by 215 · cited 1×
“For HSI classification, the spectral feature-based methods, such as support vector machine (SVM) [8], random forest (RF) [9], rotation forest (RoF) [10], canonical correlation forest (CCF) [11], [12], and multinomial logistic regression (MLR) [13], are the traditional classifiers for HSIs.”
MethodGabor-Filtering-Based Nearest Regularized Subspace for Hyperspectral Image Classification
Li, W., & Du, Q. (2014) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2013.2295313 · Cited by 192 · cited 1×
“Thereby, spectral–spatial feature-based methods, such as the gray level co-occurrence matrix [17], wavelet transform [18], and the Gabor filter [19], have been proposed to improve the discrimination of the features.”
MethodClassification of Hyperspectral Imagery Using a New Fully Convolutional Neural Network
Li, J., Zhao, X., Li, Y., Du, Q., Xi, B., & Hu, J. (2018) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2017.2786272 · Cited by 179 · cited 1×
“posed in [43] for HSI classification with an FCN, but the method is not an end-to-end classifier.”
MethodContextual deep CNN based hyperspectral classification
Lee, H., & Kwon, H. (2016) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2016.7729859 · Cited by 150 · cited 1×
“To utilize the spatial context information, a contextual CNN was proposed in [36], further improving the classification accuracy.”
MethodHyperspectral Image Classification With Canonical Correlation Forests
Xia, J., Yokoya, N., & Iwasaki, A. (2016) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2016.2607755 · Cited by 79 · cited 1×
“For HSI classification, the spectral feature-based methods, such as support vector machine (SVM) [8], random forest (RF) [9], rotation forest (RoF) [10], canonical correlation forest (CCF) [11], [12], and multinomial logistic regression (MLR) [13], are the traditional classifiers for HSIs.”
Method
Cited by
Hyperspectral Image Classification Using Group-Aware Hierarchical Transformer
Mei, S., Song, C., Ma, M., & Xu, F. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3207933 · Cited by 384
Zhu, Q., Guo, X., Deng, W., Shi, S., Guan, Q., Zhong, Y., Zhang, L., & Li, D. (2022) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2021.12.005 · Cited by 299
Self-citationZhao, C., Qin, B., Feng, S., Zhu, W., Sun, W., Li, W., & Jia, X. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3287738 · Cited by 190
“[19] first proposed the new global stochastic stratified sampling strategy and patch-free global learning”
BackgroundA review of multi-class change detection for satellite remote sensing imagery
Zhu, Q., Guo, X., Li, Z., & Li, D. (2024) · Geo-spatial Information Science · doi:10.1080/10095020.2022.2128902 · Cited by 165
“…the method of PCC, and usually different semantic segmentation DL networks were selected, such as Deeplab V3, PSPNet and FarSeg et al. (Chen et al. 2017; Zhao et al. 2017; Zheng et al. 2020b) were classified, and then multi-class of change results were obtained by comparison after classification.”
MethodTowards Energy-Efficient Hyperspectral Image Processing Inside Camera Pixels
Datta, G., Yin, Z., Jacob, A. P., Jaiswal, A. R., & Beerel, P. A. (2023) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-25075-0_22 · Cited by 5
Metadata
- Authors
- Zheng, Z., Zhong, Y., Ma, A., & Zhang, L.
- Venue
- IEEE Transactions on Geoscience and Remote Sensing
- Published
- 2020-08
- Volume
- 58
- Issue
- 8
- Pages
- 5612-5626
- ISSN
- 0196-2892 (ISSN-L)
- 1558-0644
- OpenAlex
- W3006984222
- Cited by
- 218
- References
- 50
- FWCI
- 15.19
- Type
- journal article
- Language
- en
- Open access
- green
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.