Improving Generalization for Hyperspectral Image Classification: The Impact of Disjoint Sampling on Deep Models
Source abstract
Abstract
Disjoint sampling is critical for rigorous and unbiased evaluation of state-of-the-art (SOTA) models e.g., Attention Graph and Vision Transformer. When training, validation, and test sets overlap or share data, it introduces ... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Remote-Sensing Image Classification
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (52)
Show source-provided references
1. Hyperspectral image classification-traditional to deep models: A survey for future prospects10.1109/JSTARS.2021.3133021 ↗
2. Assessment of soil salinity using explainable machine learning methods and landsat 8 images
3. Hyperspectral imaging for earth observation: Platforms and instruments10.1007/s41745-018-0070-8 ↗
4. HD-Net: High-resolution decoupled network for building footprint extraction via deeply supervised body and boundary decomposition10.1016/j.isprsjprs.2024.01.022 ↗
5. The influence of changing moisture content on laboratory acquired spectral feature parameters and mineral classification
6. Recent advances of hyperspectral imaging technology and applications in agriculture10.3390/rs12162659 ↗
7. Hyperspectral imaging: A review on UAV-based sensors, data processing and applications for agriculture and forestry10.3390/rs9111110 ↗
8. CDasXORNet: Change detection of buildings from bi-temporal remote sensing images as an XOR problem
9. LRR-Net: An interpretable deep unfolding network for hyperspectral anomaly detection
10. The use of hyperspectral remote sensing for mineral exploration: A review10.29150/jhrs.v7.4.p189-211 ↗
11. Hyperspectral imagery for environmental urban planning
12. Hyperspectral imaging in environmental monitoring: A review of recent developments and technological advances in compact field deployable systems10.3390/s19143071 ↗
13. Pande · Climate Change Impacts on Natural Resources, Ecosystems and Agricultural Systems · 2023 · 50310.1007/978-3-031-19059-9_21 ↗
14. Trustworthy remote sensing interpretation: Concepts, technologies, and applications10.1016/j.isprsjprs.2024.02.003 ↗
15. Deshpande · Hyperspectral Remote Sensing in Urban Environments · 202310.1201/9781003329312 ↗
16. Automated pixel purification for delineating pervious and impervious surfaces in a city using advanced hyperspectral imagery techniques10.1109/ACCESS.2024.3408805 ↗
17. Chauhan · Earth Observation in Urban Monitoring, Earth Observation · 2024 · 19710.1016/B978-0-323-99164-3.00007-0 ↗
18. SpectralGPT: Spectral remote sensing foundation model10.1109/TPAMI.2024.3362475 ↗
19. MSTSENet: Multiscale spectral-spatial transformer with squeeze and excitation network for hyperspectral image classification10.1016/j.engappai.2024.108669 ↗
20. A fast and compact 3-D CNN for hyperspectral image classification10.1109/LGRS.2020.3043710 ↗
21. Graph convolutional networks for hyperspectral image classification10.1109/TGRS.2020.3015157 ↗
22. Attention graph convolutional network for disjoint hyperspectral image classification10.1109/LGRS.2024.3356422 ↗
23. Extended vision transformer (ExViT) for land use and land cover classification: A multimodal deep learning framework
24. Waveformer: Spectral-spatial wavelet transformer for hyperspectral image classification10.1109/LGRS.2024.3490534 ↗
25. SCSNet: Sharpened cosine similarity-based neural network for hyperspectral image classification
26. Dual-stream class-adaptive network for semi-supervised hyperspectral image classification10.1109/TGRS.2024.3494868 ↗
27. Spatial spectral transformer with conditional position encoding for hyperspectral image classification
28. Tan · Advances in Neural Information Processing Systems · 2023 · 36
29. A disjoint samples-based 3D-CNN with active transfer learning for hyperspectral image classification10.1109/TGRS.2022.3209182 ↗
30. On the effect of spatially non-disjoint training and test samples on estimated model generalization capabilities in supervised classification with spatial features10.1109/LGRS.2017.2747222 ↗
31. Spatial prior fuzziness pool-based interactive classification of hyperspectral images10.3390/rs11091136 ↗
32. TransHSI: A hybrid CNN-transformer method for disjoint sample-based hyperspectral image classification
33. Multimodal artificial intelligence foundation models: Unleashing the power of remote sensing big data in earth observation10.59717/j.xinn-geo.2024.100055 ↗
34. UCSL: Toward unsupervised common subspace learning for cross-modal image classification
35. SpectralMamba: Efficient mamba for hyperspectral image classification
36. Cross-city matters: A multimodal remote sensing benchmark dataset for cross-city semantic segmentation using high-resolution domain adaptation networks10.1016/j.rse.2023.113856 ↗
37. Semi-active convolutional neural networks for hyperspectral image classification10.1109/TGRS.2022.3230411 ↗
38. (2+1)D extreme xception net for hyperspectral image classification10.1109/JSTARS.2024.3362936 ↗
39. Adari · Beginning Anomaly Detection Using Python-Based Deep Learning: Implement Anomaly Detection Applications with Keras and PyTorch · 2024 · 10510.1007/979-8-8688-0008-5_3 ↗
40. HybridSN: Exploring 3-D-2-D CNN feature hierarchy for hyperspectral image classification10.1109/LGRS.2019.2918719 ↗
41. Learning a 3-D-CNN and convolution transformers for hyperspectral image classification10.1109/LGRS.2024.3490534 ↗
42. Interactive spectral-spatial transformer for hyperspectral image classification10.1109/TCSVT.2024.3386578 ↗
43. Synergistic 2D/3D convolutional neural network for hyperspectral image classification
44. Hyperspectral image classification using attention-only spatial-spectral network based on transformer10.1109/ACCESS.2024.3424674 ↗
45. A light-weighted spectral-spatial transformer model for hyperspectral image classification10.1109/JSTARS.2024.3419070 ↗
46. Deep spectral spatial feature enhancement through transformer for hyperspectral image classification10.1109/LGRS.2024.3424986 ↗
47. Hybrid 3D/2D complete inception module and convolutional neural network for hyperspectral remote sensing image classification10.1007/s11063-022-10929-z ↗
48. Improved three-dimensional inception networks for hyperspectral remote sensing image classification10.1109/ACCESS.2023.3262992 ↗
49. AI-NET: Attention inception neural networks for hyperspectral image classification
50. Convolutional neural networks for multimodal remote sensing data classification10.1109/TGRS.2022.3228927 ↗
51. Hyperspectral image classification using a hybrid 3D-2D convolutional neural networks10.1109/JSTARS.2021.3099118 ↗
52. Hyperspectral image classification with deep learning models10.1109/TGRS.2018.2815613 ↗