Keywords
bidirectional feature fusion
band corruption
paired simulation
reproducibility
Abstract
We evaluated bidirectional feature fusion for hyperspectral classification under 15% band corruption. A deterministic paired simulation generated 72 cases and preserved a boundary-condition stratum. Mean spectral-spatial accuracy changed from 0.580 to 0.627; the paired difference was +0.046 (95% interval +0.044 to +0.049). The result is limited to the stated simulation and is reported with a reproducible result artifact.
References
Yang, J.-X., Wang, J., Long, Z., Sui, C., & Zhou, J. (2024). Hyperspectral Images Efficient Spatial and Spectral non-Linear Model with Bidirectional Feature Learning. arXiv. https://doi.org/10.48550/arXiv.2412.00283
Wang, H., Xuan, C., Tang, Z., Li, Q., & Song, Y. (2026). 1 SCOPE-Net: Spectral Complexity Prior Enhanced Network for Hyperspectral Image Classification. https://doi.org/10.2139/ssrn.6713370
Roy, S. K., Dubey, S. R., Chatterjee, S., & Baran Chaudhuri, B. (2020). FuSENet: fused squeeze-and-excitation network for spectral-spatial hyperspectral image classification. IET Image Processing, 14(8), 1653-1661. https://doi.org/10.1049/iet-ipr.2019.1462
Han, Y., Shi, X., Yang, S., Zhang, Y., Hong, Z., & Zhou, R. (2021). Hyperspectral Sea Ice Image Classification Based on the Spectral-Spatial-Joint Feature with the PCA Network. Remote Sensing, 13(12), 2253. https://doi.org/10.3390/rs13122253
Feng, F., Wang, S., Wang, C., & Zhang, J. (2019). Learning Deep Hierarchical Spatial-Spectral Features for Hyperspectral Image Classification Based on Residual 3D-2D CNN. Sensors, 19(23), 5276. https://doi.org/10.3390/s19235276
Reddy, T., & Harikiran, J. (2022). An outlook: machine learning in hyperspectral image classification and dimensionality reduction techniques. Journal of Spectral Imaging, a1. https://doi.org/10.1255/jsi.2022.a1
Sawant, S., & Prabukumar, M. (2020). A survey of band selection techniques for hyperspectral image classification. Journal of Spectral Imaging, a5. https://doi.org/10.1255/jsi.2020.a5
Kamala R (2026). A Hybrid Deep Learning Spectral-Spatial Graph Neural Network with Harris Hawk and Levy-Flight Optimization for Robust Hyperspectral Image Classification. Journal of Intelligent Decision Making and Information Science, 3(1s), 909-933. https://doi.org/10.59543/jidmis.v3.476
Luo, D., Liu, X., & xiong, N. (2023). The Spatial Spectral K-Nearest Neighbor Minimax Label Projection Semi-supervised Classification For Hyperspectral Remote Sensing Image. https://doi.org/10.21203/rs.3.rs-2670847/v1
Lu, Z., & He, J. (2015). Spectral-spatial hyperspectral image classification with adaptive mean filter and jump regression detection. Electronics Letters, 51(21), 1658-1660. https://doi.org/10.1049/el.2015.2259