Owing to the complex environment of hyperspectral image (HSI) collecting area, it is difficult to obtain an extensive number of labeled samples for HSI. Recently, many few-shot learning (FSL) algorithms based on convolutional neural network (CNN) have been employed for HSI classification in the scenery of small-scale training samples. However, a CNN-based model is unsuitable for modeling the spatial-spectral information with long-range dependency. The transformer has proved its superiority in modeling the long-range dependency. Inspired by this, an improved spatial-spectral transformer for HSI few-shot classification (HFC-SST) is proposed to deeply extract the local spatial-spectral information with only a few labeled samples. The contribution of this letter is twofold. First, a local spatial-spectral sequence generation method based on spatial-spectral correlation analysis and adjacent position information is proposed to generate the input sequence for transformer. Second, a local spatial-spectral feature extraction network based on the transformer is proposed to further exploit the spatial-spectral feature information on the input sequence. Experimental results on HFC with four datasets confirm that our proposed HFC-SST algorithm can achieve higher classification accuracy than the traditional CNN algorithms and the HSI FSL algorithms.
In this article, we propose a method to deposit nanocrystallite embedded carbon films by electron cyclotron resonance plasma sputtering with photon irradiation cooperated with electron or Ar+ ion irradiation. We found photon irradiation can enhance the growth of graphene nanocrystallites during carbon film deposition. The energy transfer from the photon to the metastable carbon structure excites the growth of sp2 hybridized graphene nanocrystallites, and photon-excited electrons can be accelerated by the bias and further promote the graphene nanocrystallite growth. Photons are the second quantum medium we found that can be used to deposit nanocrystallite embedded carbon films, and their quantum properties with electric neutrality can help us to further understand the formation of the carbon nanocrystallite structure and may shed light on the quantum fabrication of desired materials.
A rough substrate usually induces severe detriments limiting the performance of anti-friction materials that would lead to an increase in both the friction coefficient and wear rate. In this work, we found that a laser-induced graphene (LIG) film had a good friction adaptability on both mirror-polished and rough Si substrates. The friction coefficient of the LIG increased from 0.11 to 0.24 and the substrate roughness increased from 1.4 nm to 54.8 nm, while the wear life of the LIG was more than 20,000 cycles for both the mirror-polished and rough Si substrates. Optical microscope, Raman spectroscopy and scanning electron microscope analyses revealed a friction mechanism evolution of the LIG films on Si substrates with a different roughness. For the mirror-polished Si substrate, thick and dense graphene nanocrystallite transfer films could form on the counterpart balls, which guaranteed a long and stable wear. For the rough Si substrate, although the asperities on the rough surface would plough the counterpart balls and destabilize the transfer film formation, grooves could effectively store a compressed LIG, benefiting a stable anti-wear performance and reducing the abrasive wear at the friction interface. This work showed that a LIG film had outstanding friction adaptability on Si substrates with a different roughness and that it can be fabricated in a single-step economic process, indicating bright practical prospects in the solid lubrication fields.
Hyperspectral image (HSI) classification has attracted widespread concern in recent years. However, due to the complexity of the HSI gathering environment, it is difficult to obtain a great number of HSI labeled samples. Therefore, how to effectively extract the spatial–spectral feature with small-scale training samples is the crucial point of HSI classification. In this paper, a novel fusion framework for small-sample HSI classification is proposed to fully combine the advantages of multidimensional CNN and handcrafted features. Firstly, a 3D fuzzy histogram of oriented gradients (3D-FHOG) descriptor is proposed to fully extract the handcrafted spatial–spectral feature of HSI pixels, which is suggested to be more robust by overcoming the local spatial–spectral feature uncertainty. Secondly, a multidimensional Siamese network (MDSN), which is updated by minimizing both contrastive loss and classification loss, is designed to effectively exploit the CNN-based spatial–spectral features from multiple dimensions. Finally, the proposed MDSN combined with 3D-FHOG is utilized for small-sample HSI classification to verify the effectiveness of our proposed fusion framework. The experimental results on three public data sets indicate that the proposed MDSN combined with 3D-FHOG is significantly better than the representative handcrafted feature-based and CNN-based methods, which in turn demonstrates the superiority of the proposed fusion framework.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.