Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
158 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

BSS-Bench: Towards Reproducible and Effective Band Selection Search (2312.14570v1)

Published 22 Dec 2023 in cs.CV

Abstract: The key technology to overcome the drawbacks of hyperspectral imaging (expensive, high capture delay, and low spatial resolution) and make it widely applicable is to select only a few representative bands from hundreds of bands. However, current band selection (BS) methods face challenges in fair comparisons due to inconsistent train/validation settings, including the number of bands, dataset splits, and retraining settings. To make BS methods easy and reproducible, this paper presents the first band selection search benchmark (BSS-Bench) containing 52k training and evaluation records of numerous band combinations (BC) with different backbones for various hyperspectral analysis tasks. The creation of BSS-Bench required a significant computational effort of 1.26k GPU days. By querying BSS-Bench, BS experiments can be performed easily and reproducibly, and the gap between the searched result and the best achievable performance can be measured. Based on BSS-Bench, we further discuss the impact of various factors on BS, such as the number of bands, unsupervised statistics, and different backbones. In addition to BSS-Bench, we present an effective one-shot BS method called Single Combination One Shot (SCOS), which learns the priority of any BCs through one-time training, eliminating the need for repetitive retraining on different BCs. Furthermore, the search process of SCOS is flexible and does not require training, making it efficient and effective. Our extensive evaluations demonstrate that SCOS outperforms current BS methods on multiple tasks, even with much fewer bands. Our BSS-Bench and codes are available in the supplementary material and will be publicly available.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (56)
  1. A review of grey wolf optimizer-based feature selection methods for classification. Evolutionary Machine Learning Techniques: Algorithms and Applications, pages 273–286, 2020.
  2. Tri-cnn: a three branch model for hyperspectral image classification. Remote Sensing, 15(2):316, 2023.
  3. Ntire 2022 spectral recovery challenge and data set. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 863–881, 2022.
  4. 220 band aviris hyperspectral image data set: June 12, 1992 indian pine test site 3. Purdue University Research Repository, 10(7):991, 2015.
  5. Mst++: Multi-stage spectral-wise transformer for efficient spectral reconstruction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 745–755, 2022.
  6. Degradation-aware unfolding half-shuffle transformer for spectral compressive imaging. In NeurIPS, 2022.
  7. Hyperspectral image classification using spectral angle mapper. In 2021 IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering (WIECON-ECE), pages 87–90. IEEE, 2021.
  8. Hinet: Half instance normalization network for image restoration. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 182–192, 2021.
  9. Deep feature extraction and classification of hyperspectral images based on convolutional neural networks. IEEE Transactions on Geoscience and Remote Sensing, 54(10):6232–6251, 2016.
  10. Classification of hyperspectral images by using extended morphological attribute profiles and independent component analysis. IEEE Geoscience and Remote Sensing Letters, 8(3):542–546, 2010.
  11. An improved ant colony algorithm for optimized band selection of hyperspectral remotely sensed imagery. IEEE Access, 8:25789–25799, 2020.
  12. Nas-bench-201: Extending the scope of reproducible neural architecture search. arXiv preprint arXiv:2001.00326, 2020.
  13. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
  14. Palm-e: An embodied multimodal language model. In arXiv preprint arXiv:2303.03378, 2023.
  15. Deep reinforcement learning for semisupervised hyperspectral band selection. IEEE Transactions on Geoscience and Remote Sensing, 60:1–19, 2021.
  16. Machine learning and deep learning techniques for spectral spatial classification of hyperspectral images: A comprehensive survey. Electronics, 12(3):488, 2023.
  17. Multiple kernel learning for hyperspectral image classification: A review. IEEE Transactions on Geoscience and Remote Sensing, 55(11):6547–6565, 2017.
  18. Deep convolutional neural networks for hyperspectral image classification. Journal of Sensors, 2015:1–12, 2015.
  19. Hdnet: High-resolution dual-domain learning for spectral compressive imaging. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 17542–17551, 2022.
  20. Deep gaussian scale mixture prior for spectral compressive imaging. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 16216–16225, 2021.
  21. Improved binary particle swarm optimization for feature selection with new initialization and search space reduction strategies. Applied Soft Computing, 106:107302, 2021.
  22. Jointly learning band selection and filter array design for hyperspectral imaging. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 6384–6394, 2023.
  23. Hyperspectral band selection via difference between inter-groups. IEEE Transactions on Geoscience and Remote Sensing, 2023.
  24. Rank minimization for snapshot compressive imaging. IEEE transactions on pattern analysis and machine intelligence, 41(12):2990–3006, 2018.
  25. Self-supervised neural networks for spectral snapshot compressive imaging. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 2622–2631, 2021.
  26. l-net: Reconstruct hyperspectral images from a snapshot measurement. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 4059–4069, 2019.
  27. Microsoft. Neural Network Intelligence, 1 2021.
  28. Aio-p: Expanding neural performance predictors beyond image classification. arXiv preprint arXiv:2211.17228, 2022.
  29. Hyperspectral band selection for multispectral image classification with convolutional networks. In 2021 International Joint Conference on Neural Networks (IJCNN), pages 1–8. IEEE, 2021.
  30. Deep reinforcement learning for band selection in hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 60:1–14, 2021.
  31. Deep learning for video compressive sensing. Apl Photonics, 5(3):030801, 2020.
  32. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, 2022.
  33. Machine learning for soil moisture assessment. In Deep Learning for Sustainable Agriculture, pages 143–168. Elsevier, 2022.
  34. Hyperspectral image compression using implicit neural representation. arXiv preprint arXiv:2302.04129, 2023.
  35. Hybridsn: Exploring 3-d–2-d cnn feature hierarchy for hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters, 17(2):277–281, 2019.
  36. Band selection and classification of hyperspectral images by minimizing normalized mutual information. In Second International Conference on the Innovative Computing Technology (INTECH 2012), pages 184–189. IEEE, 2012.
  37. High-resolution hyperspectral imaging using low-cost components: Application within environmental monitoring scenarios. Sensors, 22(12):4652, 2022.
  38. A saliency-based band selection approach for hyperspectral imagery inspired by scale selection. IEEE Geoscience and Remote Sensing Letters, 15(4):572–576, 2018.
  39. Spectral–spatial feature tokenization transformer for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 60:1–14, 2022.
  40. A multiscale spectral features graph fusion method for hyperspectral band selection. IEEE Transactions on Geoscience and Remote Sensing, 60:1–12, 2021.
  41. Hyperspectral band selection via spatial-spectral weighted region-wise multiple graph fusion-based spectral clustering. In IJCAI, pages 3038–3044, 2021.
  42. A novel cubic convolutional neural network for hyperspectral image classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13:4133–4148, 2020.
  43. A simple adaptive unfolding network for hyperspectral image reconstruction. arXiv preprint arXiv:2301.10208, 2023.
  44. Neural predictor for neural architecture search. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXIX, pages 660–676. Springer, 2020.
  45. Shapley-nas: Discovering operation contribution for neural architecture search. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11892–11901, 2022.
  46. A similarity-based ranking method for hyperspectral band selection. IEEE Transactions on Geoscience and Remote Sensing, 59(11):9585–9599, 2021.
  47. Double deep q-network for hyperspectral image band selection in land cover classification applications. Remote Sensing, 15(3):682, 2023.
  48. β𝛽\betaitalic_β-darts++: Bi-level regularization for proxy-robust differentiable architecture search. arXiv preprint arXiv:2301.06393, 2023.
  49. A band selection approach for hyperspectral image based on a modified hybrid rice optimization algorithm. Symmetry, 14(7):1293, 2022.
  50. Nas-bench-101: Towards reproducible neural architecture search. In International Conference on Machine Learning, pages 7105–7114. PMLR, 2019.
  51. Plug-and-play algorithms for large-scale snapshot compressive imaging. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1447–1457, 2020.
  52. Plug-and-play algorithms for video snapshot compressive imaging. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(10):7093–7111, 2021.
  53. Surrogate nas benchmarks: Going beyond the limited search spaces of tabular nas benchmarks. In Tenth International Conference on Learning Representations, pages 1–36. OpenReview. net, 2022.
  54. Herosnet: Hyperspectral explicable reconstruction and optimal sampling deep network for snapshot compressive imaging. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 17532–17541, 2022.
  55. Spectral–spatial feature extraction for hyperspectral image classification: A dimension reduction and deep learning approach. IEEE Transactions on Geoscience and Remote Sensing, 54(8):4544–4554, 2016.
  56. Spectral–spatial residual network for hyperspectral image classification: A 3-d deep learning framework. IEEE Transactions on Geoscience and Remote Sensing, 56(2):847–858, 2017.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now