Abstract
Hyperspectral image (HSI) classification aims at predicting the pixel-wise labels in an image, where there are only a few labeled pixel samples (hard labels) for training. It is a challenging task since the classification process is susceptible to over-fitting under training with limited samples. To relieve this problem, we propose a method based on dual hierarchical learning. First, we employ a connectionist hyperspectral convolution (HC) network to capture the representations of the pixels from different receptive fields. Specifically, an HC is designed to learn the correlation among adjacent pixels and is further extended to a connectionist hierarchical structure. These operations use the correlation to enhance one-pixel learning from multiple receptive fields. Second, we analyze the properties in the hyperspectral image and introduce a hierarchical pseudo label generation algorithm to enrich the supervision of the label information. Finally, we design a dual hierarchical learning strategy to help all HC layers learn from both the hard labels and the hierarchical pseudo labels. In other words, it addresses the HSI classification problem from different views. For inference, we employ two fusion strategies to find a better prediction. The experimental results on four popular HSI benchmarks, i.e., Salinas-A, IndianPines, PaviaU, and PaviaC, demonstrate the effectiveness of the proposed method. Our code is publicly available on GitHub: https://github.com/ShuoWangCS/HSI-DHL.
- [1] . 2012. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence 34, 11 (2012), 2274–2282.Google Scholar
Digital Library
- [2] . 2016. Transductive hyperspectral image classification: Toward integrating spectral and relational features via an iterative ensemble system. Machine Learning 103, 3 (2016), 343–375.Google Scholar
Digital Library
- [3] . 2017. A novel spectral-spatial co-training algorithm for the transductive classification of hyperspectral imagery data. Pattern Recognition 63 (2017), 229–245.Google Scholar
Digital Library
- [4] . 2019. Segmentation-aided classification of hyperspectral data using spatial dependency of spectral bands. ISPRS Journal of Photogrammetry and Remote Sensing 147 (2019), 215–231.Google Scholar
Cross Ref
- [5] . 2007. Semi-supervised graph-based hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing 45, 10 (2007), 3044–3054.Google Scholar
Cross Ref
- [6] . 2017. Training convolutional neural networks for semantic classification of remote sensing imagery. In 2017 Joint Urban Remote Sensing Event (JURSE’17). IEEE, 1–4.Google Scholar
- [7] . 2000. An information-theoretic approach to spectral variability, similarity, and discrimination for hyperspectral image analysis. IEEE Transactions on Information Theory 46, 5 (2000), 1927–1932.Google Scholar
Digital Library
- [8] . 2020. Spectral-spatial hyperspectral image classification based on superpixel and multi-classifier fusion. International Journal of Remote Sensing 41, 16 (2020), 6157–6182.Google Scholar
Cross Ref
- [9] . 2019. Silica diagenesis in the Marcellus Shale: A trace element and hyperspectral cathodoluminescence study. In 6th EAGE Shale Workshop, Vol. 2019. European Association of Geoscientists & Engineers, 1–5.Google Scholar
- [10] . 2013. Semisupervised self-learning for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing 51, 7 (2013), 4032–4044.Google Scholar
Cross Ref
- [11] . 2003. Real-time constrained linear discriminant analysis to target detection and classification in hyperspectral imagery. Pattern Recognition 36, 1 (2003), 1–12.Google Scholar
Cross Ref
- [12] . 2004. Efficient graph-based image segmentation. International Journal of Computer Vision 59, 2 (2004), 167–181.Google Scholar
Digital Library
- [13] . 2014. Hyperspectral image classification through bilayer graph-based learning. IEEE Transactions on Image Processing 23, 7 (2014), 2769–2778.Google Scholar
Cross Ref
- [14] . 1998. Imaging spectroscopy and the airborne visible/infrared imaging spectrometer (AVIRIS). Remote Sensing of Environment 65, 3 (1998), 227–248.Google Scholar
Cross Ref
- [15] . 2020. Classification of hyperspectral images via multitask generative adversarial networks. IEEE Transactions on Geoscience and Remote Sensing 59, 2 (2020), 1424–1436.Google Scholar
Cross Ref
- [16] . 2005. Mapping lithology in Canada’s Arctic: Application of hyperspectral data using the minimum noise fraction transformation and matched filtering. Canadian Journal of Earth Sciences 42, 12 (2005), 2173–2193.Google Scholar
Cross Ref
- [17] . 2017. Cloud implementation of logistic regression for hyperspectral image classification. In Proceedings of the 17th International Conference on Computational and Mathematical Methods in Science and Engineering (CMMSE), Vol. 3. Cádiz, Spain: Costa Ballena (Rota), 1063–2321.Google Scholar
- [18] . 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 770–778.Google Scholar
Cross Ref
- [19] . 2017. Multi-scale 3D deep convolutional neural network for hyperspectral image classification. In 2017 IEEE International Conference on Image Processing (ICIP’17). IEEE, 3904–3908.Google Scholar
Digital Library
- [20] . 2008. Assessing the influence of reference spectra on synthetic SAM classification results. IEEE Transactions on Geoscience and Remote Sensing 46, 12 (2008), 4162–4172.Google Scholar
Cross Ref
- [21] . 2017. Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 4700–4708.Google Scholar
Cross Ref
- [22] . 2017. Deep fully convolutional network-based spatial distribution prediction for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing 55, 10 (2017), 5585–5599.Google Scholar
Cross Ref
- [23] . 2015. Adam: A method for stochastic optimization. In Proceedings of the International Conference on Learning Representations. 1–13.Google Scholar
- [24] . 2012. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems. 1097–1105.Google Scholar
Digital Library
- [25] . 1988. ROSIS (reflective optics system imaging spectrometer)-A candidate instrument for polar platform missions. In Optoelectronic Technologies for Remote Sensing from Space, Vol. 868. International Society for Optics and Photonics, 134–141.Google Scholar
- [26] . 2017. Going deeper with contextual CNN for hyperspectral image classification. IEEE Transactions on Image Processing 26, 10 (2017), 4843–4855.Google Scholar
Digital Library
- [27] . 2018. Fusing hyperspectral and multispectral images via coupled sparse tensor factorization. IEEE Transactions on Image Processing 27, 8 (2018), 4118–4130.Google Scholar
Cross Ref
- [28] . 2015. Estimation of crop LAI using hyperspectral vegetation indices and a hybrid inversion method. Remote Sensing of Environment 165 (2015), 123–134.Google Scholar
Cross Ref
- [29] . 2019. Hyperspectral image classification with deep metric learning and conditional random field. IEEE Geoscience and Remote Sensing Letters 17, 6 (2019), 1042–1046.Google Scholar
Cross Ref
- [30] . 2018. Deep few-shot learning for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing 57, 4 (2018), 2290–2304.Google Scholar
Cross Ref
- [31] . 2017. Supervised deep feature extraction for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing 56, 4 (2017), 1909–1921.Google Scholar
Cross Ref
- [32] . 2015. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 3431–3440.Google Scholar
Cross Ref
- [33] . 2018. Shorten spatial-spectral RNN with parallel-GRU for hyperspectral image classification. arXiv preprint arXiv:1810.12563 (2018).Google Scholar
- [34] . 2010. Local manifold learning-based \(k\)-nearest-neighbor for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing 48, 11 (2010), 4099–4109.Google Scholar
- [35] . 2004. Classification of hyperspectral remote sensing images with support vector machines. IEEE Transactions on Geoscience and Remote Sensing 42, 8 (2004), 1778–1790.Google Scholar
Cross Ref
- [36] . 2020. Scalable recurrent neural network for hyperspectral image classification. Journal of Supercomputing 76, 11 (2020), 8866–8882.Google Scholar
Digital Library
- [37] . 2019. HybridSN: Exploring 3-D–2-D CNN feature hierarchy for hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters 17, 2 (2019), 277–281.Google Scholar
Cross Ref
- [38] . 2020. Attention-based adaptive spectral-spatial kernel resnet for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing 59, 9 (2020), 7831–7843.Google Scholar
Cross Ref
- [39] . 2020. An unsupervised labeling approach for hyperspectral image classification. International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences 43 (2020), 407–415.Google Scholar
Cross Ref
- [40] . 2020. Efficient deep learning of nonlocal features for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing 59, 7 (2020), 6029–6043.Google Scholar
Cross Ref
- [41] . 2015. A novel semi-supervised hyperspectral image classification approach based on spatial neighborhood information and classifier combination. ISPRS Journal of Photogrammetry and Remote Sensing 105 (2015), 19–29.Google Scholar
Cross Ref
- [42] . 2016. Seven ways to improve example-based single image super resolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1865–1873.Google Scholar
Cross Ref
- [43] . 2011. Hyperspectral image classification with independent component discriminant analysis. IEEE Transactions on Geoscience and Remote Sensing 49, 12 (2011), 4865–4876.Google Scholar
Cross Ref
- [44] . 2014. Semi-supervised classification for hyperspectral imagery based on spatial-spectral label propagation. ISPRS Journal of Photogrammetry and Remote Sensing 97 (2014), 123–137.Google Scholar
Cross Ref
- [45] . 2018. Deep unsupervised saliency detection: A multiple noisy labeling perspective. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 9029–9038.Google Scholar
Cross Ref
- [46] . 2011. On combining multiple features for hyperspectral remote sensing image classification. IEEE Transactions on Geoscience and Remote Sensing 50, 3 (2011), 879–893.Google Scholar
Cross Ref
- [47] . 2020. FPGA: Fast patch-free global learning framework for fully end-to-end hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing 58, 8 (2020), 5612–5626.Google Scholar
Cross Ref
- [48] . 2010. Learning conditional random fields for classification of hyperspectral images. IEEE Transactions on Image Processing 19, 7 (2010), 1890–1907.Google Scholar
Digital Library
- [49] . 2017. Spectral–spatial residual network for hyperspectral image classification: A 3-D deep learning framework. IEEE Transactions on Geoscience and Remote Sensing 56, 2 (2017), 847–858.Google Scholar
Cross Ref
- [50] . 2019. Pyramid fully convolutional network for hyperspectral and multispectral image fusion. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 12, 5 (2019), 1549–1558.Google Scholar
Cross Ref
- [51] . 2015. Learning hierarchical spectral–spatial features for hyperspectral image classification. IEEE Transactions on Cybernetics 46, 7 (2015), 1667–1678.Google Scholar
Cross Ref
- [52] . 2021. A spectral-spatial-dependent global learning framework for insufficient and imbalanced hyperspectral image classification. IEEE Transactions on Cybernetics (2021).Google Scholar
- [53] . 2020. A spectral-spatial-dependent global learning framework for insufficient and imbalanced hyperspectral image classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 13 (2020), 659–674.Google Scholar
Cross Ref
Index Terms
Boosting Hyperspectral Image Classification with Dual Hierarchical Learning
Recommendations
Collaborative learning for hyperspectral image classification
Recently, collaborative learning (CL) is introduced to combine active learning (AL) with semi-supervised learning (SSL), and solve the problem of limited training samples. In this paper, we proposed a novel CL framework for hyperspectral image ...
Unified active and semi-supervised learning for hyperspectral image classification
AbstractThe large-scale labeled data is very crucial to train a classification model with strong generalization ability. However, the collection of large-scale labeled data is very expensive, especially in the remote sensing fields. The available of ...
A discriminant sparse representation graph-based semi-supervised learning for hyperspectral image classification
The classification of hyperspectral image with a paucity of labeled samples is a challenging task. In this paper, we present a discriminant sparse representation (DSR) graph for semi-supervised learning (SSL) to address this problem. For graph-based ...






Comments