One-shot neural band selection for spectral recovery

• URL: http://arxiv.org/abs/2305.09236v1
• Date: Tue, 16 May 2023 07:34:03 GMT
• Title: One-shot neural band selection for spectral recovery
• Authors: Hai-Miao Hu, Zhenbo Xu, Wenshuai Xu, You Song, YiTao Zhang, Liu Liu, Zhilin Han, Ajin Meng
• Abstract summary: We present a novel one-shot Neural Band Selection (NBS) framework for spectral recovery. Our NBS is based on the continuous relaxation of the band selection process, thus allowing efficient band search using gradient descent. Our code will be publicly available.
• Score: 15.565913045545066
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Band selection has a great impact on the spectral recovery quality. To solve this ill-posed inverse problem, most band selection methods adopt hand-crafted priors or exploit clustering or sparse regularization constraints to find most prominent bands. These methods are either very slow due to the computational cost of repeatedly training with respect to different selection frequencies or different band combinations. Many traditional methods rely on the scene prior and thus are not applicable to other scenarios. In this paper, we present a novel one-shot Neural Band Selection (NBS) framework for spectral recovery. Unlike conventional searching approaches with a discrete search space and a non-differentiable search strategy, our NBS is based on the continuous relaxation of the band selection process, thus allowing efficient band search using gradient descent. To enable the compatibility for se- lecting any number of bands in one-shot, we further exploit the band-wise correlation matrices to progressively suppress similar adjacent bands. Extensive evaluations on the NTIRE 2022 Spectral Reconstruction Challenge demonstrate that our NBS achieves consistent performance gains over competitive baselines when examined with four different spectral recov- ery methods. Our code will be publicly available.

Related papers

• Correlation-Based Band Selection for Hyperspectral Image Classification [0.0]
  We present a correlation-based band selection approach for hyperspectral image classification. Our approach calculates the average correlation between bands using correlation coefficients to identify the relationships among different bands. This allows us to isolate and retain bands that exhibit lower inter-band dependencies, ensuring that the selected bands provide diverse and non-redundant information.
  arXiv  Detail & Related papers  (2025-01-24T09:03:27Z)
• Neural Dueling Bandits [58.90189511247936]
  We use a neural network to estimate the reward function using preference feedback for the previously selected arms. We then extend our theoretical results to contextual bandit problems with binary feedback, which is in itself a non-trivial contribution.
  arXiv  Detail & Related papers  (2024-07-24T09:23:22Z)
• Embedded Hyperspectral Band Selection with Adaptive Optimization for Image Semantic Segmentation [0.0]
  This paper introduces a pioneering approach for hyperspectral band selection that offers an embedded solution. Our proposed method, embedded hyperspectral band selection (EHBS), excels in selecting the best bands without needing prior processing. We conduct experiments on two distinct semantic-segmentation hyperspectral benchmark datasets, demonstrating their superiority in terms of accuracy and ease of use.
  arXiv  Detail & Related papers  (2024-01-21T07:48:39Z)
• BSS-Bench: Towards Reproducible and Effective Band Selection Search [8.712706386559171]
  This paper presents the first band selection search benchmark (BSS-Bench) for various hyperspectral analysis tasks. The creation of BSS-Bench required a significant computational effort of 1.26k GPU days. 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.
  arXiv  Detail & Related papers  (2023-12-22T10:00:32Z)
• End-to-end Hyperspectral Image Change Detection Network Based on Band Selection [22.7908026248101]
  We propose an end-to-end hyperspectral image change detection network with band selection (ECDBS) The main ingredients of the network are a deep learning based band selection module and cascading band-specific spatial attention blocks. Experimental evaluations conducted on three widely used HSI-CD datasets demonstrate the effectiveness and superiority of our proposed method.
  arXiv  Detail & Related papers  (2023-07-23T13:50:41Z)
• UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning [89.56465237941013]
  We propose UNICON, a simple yet effective sample selection method which is robust to high label noise. We obtain an 11.4% improvement over the current state-of-the-art on CIFAR100 dataset with a 90% noise rate.
  arXiv  Detail & Related papers  (2022-03-28T07:36:36Z)
• Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection [11.926787216956459]
  We propose a novel Omni-frequency Channel-selection Reconstruction (OCR-GAN) network to handle anomaly detection task in a perspective of frequency. We show that our approach markedly surpasses the reconstruction-based baseline by +38.1 and the current SOTA method by +0.3.
  arXiv  Detail & Related papers  (2022-03-01T06:35:15Z)
• Optimal Clustering with Bandit Feedback [57.672609011609886]
  This paper considers the problem of online clustering with bandit feedback. It includes a novel stopping rule for sequential testing that circumvents the need to solve any NP-hard weighted clustering problem as its subroutines. We show through extensive simulations on synthetic and real-world datasets that BOC's performance matches the lower boundally, and significantly outperforms a non-adaptive baseline algorithm.
  arXiv  Detail & Related papers  (2022-02-09T06:05:05Z)
• Syndicated Bandits: A Framework for Auto Tuning Hyper-parameters in Contextual Bandit Algorithms [74.55200180156906]
  The contextual bandit problem models the trade-off between exploration and exploitation. We show our Syndicated Bandits framework can achieve the optimal regret upper bounds.
  arXiv  Detail & Related papers  (2021-06-05T22:30:21Z)
• Hyperspectral Band Selection for Multispectral Image Classification with Convolutional Networks [0.0]
  We propose a novel band selection method to select a reduced set of wavelengths from hyperspectral images. We show that our method produces more suitable results for a multispectral sensor design.
  arXiv  Detail & Related papers  (2021-06-01T17:24:35Z)
• Jo-SRC: A Contrastive Approach for Combating Noisy Labels [58.867237220886885]
  We propose a noise-robust approach named Jo-SRC (Joint Sample Selection and Model Regularization based on Consistency) Specifically, we train the network in a contrastive learning manner. Predictions from two different views of each sample are used to estimate its "likelihood" of being clean or out-of-distribution.
  arXiv  Detail & Related papers  (2021-03-24T07:26:07Z)
• Deep Reinforcement Learning for Band Selection in Hyperspectral Image Classification [21.098473348205726]
  Band selection refers to the process of choosing the most relevant bands in a hyperspectral image. In this paper, we are interested in training an intelligent agent that is capable of automatically learning policy to select an optimal band subset. We frame the problem of unsupervised band selection as a Markov decision process, propose an effective method to parameterize it, and finally solve the problem by deep reinforcement learning.
  arXiv  Detail & Related papers  (2021-03-15T22:06:15Z)
• Batched Neural Bandits [107.5072688105936]
  BatchNeuralUCB combines neural networks with optimism to address the exploration-exploitation tradeoff. We prove that BatchNeuralUCB achieves the same regret as the fully sequential version while reducing the number of policy updates considerably.
  arXiv  Detail & Related papers  (2021-02-25T17:36:44Z)
• Upper Confidence Bounds for Combining Stochastic Bandits [52.10197476419621]
  We provide a simple method to combine bandit algorithms. Our approach is based on a "meta-UCB" procedure that treats each of $N$ individual bandit algorithms as arms in a higher-level $N$-armed bandit problem.
  arXiv  Detail & Related papers  (2020-12-24T05:36:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.