Abstract
The spectral anomalies, limited training samples, and noisy training labels pose significant challenges to accurately classifying hyperspectral images (HSIs). To address these issues, we propose a novel dictionary cache transformer (DiCT) for HSIs classification, leveraging a combination of a group self-attention mechanism and a dictionary cache module. Specifically, the group self-attention mechanism binds the features local to the pixel into a group, thus alleviating the interference caused by pixel spectral anomalies. Furthermore, we capture representative structural information from different samples using their discriminative features to construct the dictionary cache module. The dictionary cache module enhances features by fusing sample features and the most similar element in the dictionary cache, thus improving the model’s resilience to noisy training labels. Experiments on five HSIs datasets demonstrate the proposed DiCT’s superiority in classification performance and robustness to noisy training labels.
Similar content being viewed by others
References
Adão T, Hruška J, Pádua L, Bessa J, Peres E, Morais R, Sousa J (2017) Hyperspectral imaging: A review on UAV-based sensors, data processing and applications for agriculture and forestry. Remote Sens 9(11):1110. https://doi.org/10.3390/rs9111110
Zhong Y, Wang X, Xu Y, Wang S, Jia T, Hu X, Zhao J, Wei L, Zhang L (2018) Mini-UAVborne hyperspectral remote sensing: From observation and processing to applications. IEEE Geosci Remote Sens Mag 6(4):46–62. https://doi.org/10.1109/mgrs.2018.2867592
Maxwell AE, Warner TA, Fang F (2018) Implementation of machine-learning classification in remote sensing: an applied review. Int. J. Remote Sens. 39(9):2784–2817. https://doi.org/10.1080/01431161.2018.1433343
Zhao J, Zhong Y, Hu X, Wei L, Zhang L (2020) A robust spectral-spatial approach to identifying heterogeneous crops using remote sensing imagery with high spectral and spatial resolutions. Remote Sens Environ 239:111605. https://doi.org/10.1016/j.rse.2019.111605
Ang KL, Seng JK (2021) Big data and machine learning with hyperspectral information in agriculture. IEEE Access 9:36699–36718. https://doi.org/10.1109/ACCESS.2021.3051196
Aruffo E, Chiuri A, Angelini F, Artuso F, Cataldi D, Colao F, Fiorani L, Menicucci I, Nuvoli M, Pistilli M, Spizzichino V, Palucci A (2020) Hyperspectral fluorescence LIDAR based on a liquid crystal tunable filter for marine environment monitoring. Sensors 20(2):410. https://doi.org/10.3390/s20020410
Thiele ST, Bnoulkacem Z, Lorenz S, Bordenave A, Menegoni N, Madriz Y, Dujoncquoy E, Gloaguen R, Kenter J (2022) Mineralogical mapping with accurately corrected shortwave infrared hyperspectral data acquired obliquely from uavs. Remote Sens 14(1). https://doi.org/10.3390/rs14010005
Kumar B, Dikshit O, Gupta A, Singh MK (2020) Feature extraction for hyperspectral image classification: a review. Int J Remote Sens 41(16):6248–6287. https://doi.org/10.1080/01431161.2020.1736732
Ghamisi P, Plaza J, Chen Y, Li J, Plaza AJ (2017) Advanced spectral classifiers for hyperspectral images: A review. IEEE Geosci Remote Sens Mag 5(1):8–32. https://doi.org/10.1109/MGRS.2016.2616418
Mu C, Zeng Q, Liu Y, Qu Y (2021) A two-branch network combined with robust principal component analysis for hyperspectral image classification. IEEE Geosci Remote Sens Lett 18(12):2147–2151. https://doi.org/10.1109/LGRS.2020.3013707
Jayaprakash C, Damodaran BB, Viswanathan S, Soman KP (2020) Randomized independent component analysis and linear discriminant analysis dimensionality reduction methods for hyperspectral image classification. J Appl Remote Sens 14(3):1–24. https://doi.org/10.1117/1.JRS.14.036507
Yu H, Xu Z, Wang Y, Jiao T, Guo Q (2021) The use of kpca over subspaces for cross-scale superpixel based hyperspectral image classification. Remote Sens Lett 12(5):470–477. https://doi.org/10.1080/2150704X.2021.1897180
Zhang L, Zhang L, Du B, You J, Tao D (2019) Hyperspectral image unsupervised classification by robust manifold matrix factorization. Inf Sci 485:154–169. https://doi.org/10.1016/j.ins.2019.02.008
Huang W, Huang Y, Wu Z, Yin J, Chen Q (2021) A multi-kernel mode using a local binary pattern and random patch convolution for hyperspectral image classification. IEEE J Sel Top Appl Earth Observ Remote Sens 14:4607–4620. https://doi.org/10.1109/JSTARS.2021.3076198
Cao D, Zhang M, Li W, Ran Q (2021) Hyperspectral and infrared image collaborative classification based on morphology feature extraction. IEEE J Sel Top Appl Earth Observ Remote Sens 14:4405–4416. https://doi.org/10.1109/JSTARS.2021.3072843
Paoletti ME, Haut JM, Plaza J, Plaza A (2019) Deep learning classifiers for hyperspectral imaging: A review. ISPRS-J Photogramm Remote Sens 158:279–317. https://doi.org/10.1016/j.isprsjprs.2019.09.006
Lu X, Zheng X, Yuan Y (2017) Remote sensing scene classification by unsupervised representation learning. IEEE Trans. Geosci. Remote. Sens. 55(9):5148–5157. https://doi.org/10.1109/TGRS.2017.2702596
Han K, Wang Y, Chen H, Chen X, Guo J, Liu Z, Tang Y, Xiao A, Xu C, Xu Y, Yang Z, Zhang Y, Tao D (2023) A survey on vision transformer. IEEE Trans. Pattern Anal. Mach. Intell. 45(1):87–110. https://doi.org/10.1109/TPAMI.2022.3152247
Espinosa F, Bartolomé A, Hernández PV, Rodriguez-Sánchez MC (2022) Contribution of singular spectral analysis to forecasting and anomalies detection of indoors air quality. Sensors 22(8):3054. https://doi.org/10.3390/s22083054
Zhou H, Zhang X, Zhang C, Ma Q (2023) Quaternion convolutional neural networks for hyperspectral image classification. Eng Appl Artif Intell 123:106234. https://doi.org/10.1016/j.engappai.2023.106234
Zhou H, Zhang X, Zhang C, Ma Q (2023) Vision transformer with contrastive learning for hyperspectral image classification. IEEE Geosci Remote Sens Lett 20:1–5. https://doi.org/10.1109/LGRS.2023.3255867
Zhang X, Sun Y, Jiang K, Li C, Jiao L, Zhou H (2018) Spatial sequential recurrent neural network for hyperspectral image classification. IEEE J Sel Top Appl Earth Observ Remote Sens 11(11):4141–4155. https://doi.org/10.1109/JSTARS.2018.2844873
Ghaderizadeh S, Abbasi-Moghadam D, Sharifi A, Zhao N, Tariq A (2021) Hyperspectral image classification using a hybrid 3d–2d convolutional neural networks. IEEE J Sel Top Appl Earth Observ Remote Sens 14:7570–7588. https://doi.org/10.1109/JSTARS.2021.3099118
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, June 27-30, 2016, pp. 770–778. https://doi.org/10.1109/CVPR.2016.90
de Santana Correia A, Colombini EL (2022) Attention, please! a survey of neural attention models in deep learning Artif Intell Rev. https://doi.org/10.1007/s10462-022-10148-x
Sabour S, Frosst N, Hinton GE (2017) Dynamic routing between capsules. In: Guyon I, von Luxburg U, Bengio S, Wallach HM, Fergus R, Vishwanathan SVN, Garnett R (eds) Advances in Neural Information Processing Systems 30. Long Beach, CA, USA, pp 3856–3866
Zhou H, Zhang C, Zhang X, Ma Q (2023) Image classification based on quaternion-valued capsule network. Appl Intell 53(5):5587–5606. https://doi.org/10.1007/s10489-022-03849-x
Zhang M, Luo H, Song W, Mei H, Su C (2021) Spectral-spatial offset graph convolutional networks for hyperspectral image classification. Remote Sens 13(21):4342–4364. https://doi.org/10.3390/rs13214342
Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In: 2021 IEEE/CVF International Conference on Computer Vision, pp. 9992–10002. https://doi.org/10.1109/ICCV48922.2021.00986
Yang X, Cao W, Lu Y, Zhou Y (2022) Hyperspectral image transformer classification networks. IEEE Trans Geosci Remote Sensing 60:1–15. https://doi.org/10.1109/TGRS.2022.3171551
Qing Y, Liu W, Feng L, Gao W (2021) Improved transformer net for hyperspectral image classification. Remote Sens 13(11). https://doi.org/10.3390/rs13112216
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: 2017 31st Conference on Neural Information Processing Systems,NRPS. NIPS’17, pp. 6000–6010. Curran Associates Inc., Red Hook, NY, USA
Wang S, Cai J, Lin Q, Guo W (2019) An overview of unsupervised deep feature representation for text categorization. IEEE Trans Comput Soc Syst 6(3):504–517. https://doi.org/10.1109/TCSS.2019.2910599
Sun L, Zou H, Wei J, Cao X, He S, Li M, Liu S (2023) Semantic segmentation of highresolution remote sensing images based on sparse self-attention and feature alignment. Remote Sens 15(6):1598. https://doi.org/10.3390/rs15061598
Chen CR, Fan Q, Panda R (2021) Crossvit: Cross-attention multi-scale vision transformer for image classification. In: 2021 IEEE/CVF International Conference on Computer Vision, pp. 347–356. https://doi.org/10.1109/ICCV48922.2021.00041
Jiang J, Ma J, Liu X (2022) Multilayer spectral-spatial graphs for label noisy robust hyperspectral image classification. IEEE Trans Neural Netw Learn Syst 33(2):839–852. https://doi.org/10.1109/TNNLS.2020.3029523
Tu B, Zhang X, Kang X, Zhang G, Li S (2019) Density peak-based noisy label detection for hyperspectral image classification. IEEE Trans Geosci Remote Sensing 57(3):1573–1584. https://doi.org/10.1109/tgrs.2018.2867444
Tu B, Zhou C, Liao X, Xu Z, Peng Y, Ou X (2020) Hierarchical structure-based noisy labels detection for hyperspectral image classification. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 13:2183–2199. https://doi.org/10.1109/jstars.2020.2994162
Zhang W, Wang D, Tan X (2018) Robust class-specific autoencoder for data cleaning and classification in the presence of label noise. Neural Process. Lett 50(2):1845–1860. https://doi.org/10.1007/s11063-018-9963-9
Wang Y, Ma X, Chen Z, Luo Y, Yi J, Bailey J (2019) Symmetric cross entropy for robust learning with noisy labels. In: 2019 16th Proceedings of the IEEE/CVF International Conference on Computer Vision,ICCV, pp. 322–330
Ghosh A, Kumar H, Sastry PS (2017) Robust loss functions under label noise for deep neural networks. Proceedings of the AAAI Conference on Artificial Intelligence 31(1). https://doi.org/10.1609/aaai.v31i1.10894
Vane G, Green R, Chrien T, Enmark H, Hansen E, Porter W (1993) The airborne visible/ infrared imaging spectrometer (aviris). Remote Sens Environ 44(2):127–143. https://doi.org/10.1016/0034-4257(93)90012-M. Airbone Imaging Spectrometry
Zhong Y, Hu X, Luo C, Wang X, Zhao J, Zhang L (2020) WHU-hi: UAV-borne hyperspectral with high spatial resolution (h2) benchmark datasets and classifier for precise crop identification based on deep convolutional neural network with CRF. Remote Sens Environ 250:112012. https://doi.org/10.1016/j.rse.2020.112012
Cen Y, Zhang L, Zhang X, Wang Y, Qi W, Tang S, Zhang P (2020) Aerial hyperspectral remote sensing classification dataset of xiongan new area (matiwan village). J Remote Sensing 24(11):1299–1306. https://doi.org/10.11834/jrs.20209065
Mantas CJ, Castellano JG, Moral-García S, Abellán J (2018) A comparison of random forest based algorithms: random credal random forest versus oblique random forest. Soft Comput 23(21):10739–10754. https://doi.org/10.1007/s00500-018-3628-5
Liu H, Dai Z, So D, Le QV (2021) Pay attention to mlps. In: 2021 34th Advances in Neural Information Processing Systems,NIPS 34:9204–9215. https://doi.org/10.48550/arXiv.2105.08050
Chen S, Xie E, GE C, Chen R, Liang D, Luo P (2022) CycleMLP: A MLP-like architecture for dense prediction. In: 2022 10th International Conference on Learning Representations, ICLR, pp. 1–11
Paoletti ME, Haut JM, Fernandez-Beltran R, Plaza J, Plaza A, Li J, Pla F (2019) Capsule networks for hyperspectral image classification. IEEE Trans. Geosci. Remote Sensing 57(4):2145–2160. https://doi.org/10.1109/tgrs.2018.2871782
Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N (2021) An image is worth 16x16 words: Transformers for image recognition at scale. In: 2021 5th International Conference on Learning Representations, ICLR, pp. 1–21
Xu Y, Li Z, Li W, Du Q, Liu C, Fang Z, Zhai L (2022) Dual-channel residual network for hyperspectral image classification with noisy labels. IEEE Trans Geosci Remote Sensing 60:1–11. https://doi.org/10.1109/tgrs.2021.3057689
Loshchilov I, Hutter F (2019) Decoupled weight decay regularization. In: 7th International Conference on Learning Representations, pp. 1–18
Van der Maaten L, Hinton G (2008) Visualizing data using t-sne. J Mach Learn Res 9(11):2579–2605
Acknowledgements
The authors would like to express their gratitude to the reviewers for their insightful remarks and ideas on how to improve the paper’s quality.
Funding
This work was supported by the National Natural Science Foundation of China (Nos. 11871104 and 12131006).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interests
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhou, H., Zhang, X., Zhang, C. et al. Dictionary cache transformer for hyperspectral image classification. Appl Intell 53, 26725–26749 (2023). https://doi.org/10.1007/s10489-023-04934-5
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-023-04934-5