One-shot neural band selection for spectral recovery

by   Hai-Miao Hu, et al.

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.


page 1

page 2

page 3

page 4


Spectral band selection for vegetation properties retrieval using Gaussian processes regression

With current and upcoming imaging spectrometers, automated band analysis...

BS-Nets: An End-to-End Framework For Band Selection of Hyperspectral Image

Hyperspectral image (HSI) consists of hundreds of continuous narrow band...

Band selection in RKHS for fast nonlinear unmixing of hyperspectral images

The profusion of spectral bands generated by the acquisition process of ...

Native Multi-Band Audio Coding within Hyper-Autoencoded Reconstruction Propagation Networks

Spectral sub-bands do not portray the same perceptual relevance. In audi...

Optimal Use of Multi-spectral Satellite Data with Convolutional Neural Networks

The analysis of satellite imagery will prove a crucial tool in the pursu...

Band Relevance Factor (BRF): a novel automatic frequency band selection method based on vibration analysis for rotating machinery

The monitoring of rotating machinery has now become a fundamental activi...

Out-of-Band Power Reduction in NC-OFDM with Optimized Cancellation Carriers Selection

In this letter, we propose a computationally efficient method for joint ...

Please sign up or login with your details

Forgot password? Click here to reset