Contrastive Learning for Regression on Hyperspectral Data (2403.17014v1)
Abstract: Contrastive learning has demonstrated great effectiveness in representation learning especially for image classification tasks. However, there is still a shortage in the studies targeting regression tasks, and more specifically applications on hyperspectral data. In this paper, we propose a contrastive learning framework for the regression tasks for hyperspectral data. To this end, we provide a collection of transformations relevant for augmenting hyperspectral data, and investigate contrastive learning for regression. Experiments on synthetic and real hyperspectral datasets show that the proposed framework and transformations significantly improve the performance of regression models, achieving better scores than other state-of-the-art transformations.
- “Hybridsn: Exploring 3-d–2-d cnn feature hierarchy for hyperspectral image classification,” IEEE Geoscience and Remote Sensing Letters, vol. 17, no. 2, pp. 277–281, 2019.
- “Deep learning based regression for optically inactive inland water quality parameter estimation using airborne hyperspectral imagery,” Environmental Pollution, vol. 286, pp. 117534, 2021.
- “End-to-end convolutional autoencoder for nonlinear hyperspectral unmixing,” Remote Sensing, vol. 14, no. 14, pp. 3341, 2022.
- “Object detection in hyperspectral images,” IEEE Signal Processing Letters, vol. 28, pp. 508–512, 2021.
- “A simple framework for contrastive learning of visual representations,” in International conference on machine learning. PMLR, 2020, pp. 1597–1607.
- “Nearest neighbor-based contrastive learning for hyperspectral and lidar data classification,” IEEE Transactions on Geoscience and Remote Sensing, 2023.
- “Unlocking the potential of data augmentation in contrastive learning for hyperspectral image classification,” Remote Sensing, vol. 15, no. 12, pp. 3123, 2023.
- “Deep spatial-spectral subspace clustering for hyperspectral images based on contrastive learning,” Remote Sensing, vol. 13, no. 21, pp. 4418, 2021.
- “A hyperspectral image change detection framework with self-supervised contrastive learning pretrained model,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 15, pp. 7724–7740, 2022.
- “Superpixel contracted neighborhood contrastive subspace clustering network for hyperspectral images,” IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1–13, 2022.
- “Self supervised learning for few shot hyperspectral image classification,” in IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2022, pp. 267–270.
- “Contrastive learning approach for blind hyperspectral unmixing (clhu),” Authorea Preprints, 2023.
- Bruce Hapke, “Bidirectional reflectance spectroscopy: 1. theory,” Journal of Geophysical Research: Solid Earth, vol. 86, no. B4, pp. 3039–3054, 1981.
- “A novel endmember bundle extraction and clustering approach for capturing spectral variability within endmember classes,” IEEE Transactions on Geoscience and Remote Sensing, vol. 54, no. 11, pp. 6712–6731, 2016.
- “The us geological survey, digital spectral library: Version 1: 0.2 to 3.0 mum,” in Bulletin of the American astronomical society, 1993, vol. 25, p. 1033.
- “Hyperspectral imaging for the evaluation of lithology and the monitoring of hydrocarbons in environmental samples,” in RemTech (International event on Remediation, Coasts, Floods, Climate, Seismic, Regeneration Industry), 2021.