Yufei Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yufei Liu has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Xiaorun Li
College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China
5 shared publications - Ziqiang Hua
Zhejiang Lab, Hangzhou, Zhejiang, China
4 shared publications - Liaoying Zhao
Hangzhou Dianzi University
2 shared publications - Risheng Huang
Shaoxing University
2 shared publications - Shaowei Jiang
Hangzhou Dianzi University, Hangzhou, China
2 shared publications - Chaoqun Xia
College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou 325035, China
1 shared publication
Latest Publications
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19, 35596-35609
Unsupervised Hyperspectral Band Selection via Transformer-Based Spectral–Spatial Reconstruction Network
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19, 35596-35609
Open AccessUnsupervised Hyperspectral Band Selection via Transformer-Based Spectral–Spatial Reconstruction Network
- Open Access
- 25 November 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (23) , 5495
An Unsupervised Band Selection Method via Contrastive Learning for Hyperspectral Images
Band selection (BS) is an efficacious approach to reduce hyperspectral information redundancy while preserving the physical meaning of hyperspectral images (HSIs). Recently, deep learning-based BS methods have received widespread interest due to their ability to model the nonlinear relationship between bands, with existing methods typically relying on generative algorithms. However, the process of generating images with pixel-level detail required by generative algorithm-based BS methods is computationally expensive. To alleviate this issue, we propose a contrastive learning-based unsupervised BS architecture, termed ContrastBS, in this article. With the help of contrastive learning, the proposed architecture avoids the costly generation step in pixel space by learning to distinguish data at the abstract semantic level of the feature space. Specifically, ContrastBS combines an attention mechanism with contrastive learning to extract the importance of each band. Furthermore, we design a novel loss function, which is able to constrain the symmetric loss while ensuring attention to the most valuable bands, for the contrastive learning-based BS network. Experimental results indicate that ContrastBS has excellent classification performance and competitive time cost compared to the comparison methods.
- 25 November 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (23) , 5495
Open AccessAn Unsupervised Band Selection Method via Contrastive Learning for Hyperspectral Images
Band selection (BS) is an efficacious approach to reduce hyperspectral information redundancy while preserving the physical meaning of hyperspectral images (HSIs). Recently, deep learning-based BS methods have received widespread interest due to their ability to model the nonlinear relationship between bands, with existing methods typically relying on generative algorithms. However, the process of generating images with pixel-level detail required by generative algorithm-based BS methods is computationally expensive. To alleviate this issue, we propose a contrastive learning-based unsupervised BS architecture, termed ContrastBS, in this article. With the help of contrastive learning, the proposed architecture avoids the costly generation step in pixel space by learning to distinguish data at the abstract semantic level of the feature space. Specifically, ContrastBS combines an attention mechanism with contrastive learning to extract the importance of each band. Furthermore, we design a novel loss function, which is able to constrain the symmetric loss while ensuring attention to the most valuable bands, for the contrastive learning-based BS network. Experimental results indicate that ContrastBS has excellent classification performance and competitive time cost compared to the comparison methods.
- 21 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 20 (1545598X) , 1-5
BSFormer: Transformer-Based Reconstruction Network for Hyperspectral Band Selection
Band selection (BS) is an effective approach to alleviate the spectral redundancy of a hyperspectral image (HSI). The emerging deep learning-based BS methods have become a hot topic due to their ability to model nonlinear relationships between spectral bands. However, existing deep learning-based BS methods fail to accurately extract the representativeness of each band as a result of the limitation of interpretation networks. Moreover, existing deep learning methods cannot fully utilize the inter-band correlation and the spatial information of HSIs for BS. To solve these issues, in this letter, we propose a novel transformer reconstruction network for unsupervised BS, termed BSFormer. Specifically, the transformer reconstruction network, which contributes to leveraging the spectral-spatial information of the HSI, consists of a transformer-based band attention (TBA) module and a convolutional autoencoder-based reconstruction module. On this basis, we design a novel band evaluation criterion composed of representative metric and redundancy metric, which are interpreted with the help of the multi-head self-attention layer in the TBA module. The designed criterion can fully use the band representativeness and inter-band correlation for BS. Experimental results on three well-known hyperspectral data sets verify that the proposed BSFormer can yield better classification performance than the competitors.
- 21 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 20 (1545598X) , 1-5
BSFormer: Transformer-Based Reconstruction Network for Hyperspectral Band Selection
Band selection (BS) is an effective approach to alleviate the spectral redundancy of a hyperspectral image (HSI). The emerging deep learning-based BS methods have become a hot topic due to their ability to model nonlinear relationships between spectral bands. However, existing deep learning-based BS methods fail to accurately extract the representativeness of each band as a result of the limitation of interpretation networks. Moreover, existing deep learning methods cannot fully utilize the inter-band correlation and the spatial information of HSIs for BS. To solve these issues, in this letter, we propose a novel transformer reconstruction network for unsupervised BS, termed BSFormer. Specifically, the transformer reconstruction network, which contributes to leveraging the spectral-spatial information of the HSI, consists of a transformer-based band attention (TBA) module and a convolutional autoencoder-based reconstruction module. On this basis, we design a novel band evaluation criterion composed of representative metric and redundancy metric, which are interpreted with the help of the multi-head self-attention layer in the TBA module. The designed criterion can fully use the band representativeness and inter-band correlation for BS. Experimental results on three well-known hyperspectral data sets verify that the proposed BSFormer can yield better classification performance than the competitors.
- 30 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 19 (1545598X) , 1-5
A Band Selection Method With Masked Convolutional Autoencoder for Hyperspectral Image
Band selection (BS) is an effective means to solve the problems of spectral redundancy and Hughes phenomenon in hyperspectral images (HSIs). However, existing BS methods fail to consider the representativeness, redundancy, and information content of the selected bands simultaneously, and most of them lack consideration of the inherent nonlinear relationship between bands. To address these problems, we propose a novel unsupervised BS framework that can comprehensively consider band representativeness, redundancy, and information content (RRI) in this letter. The band representativeness is estimated by a convolutional autoencoder (AE), which can capture the inherent nonlinear relationship between the bands and leverage the spatial information of the HSI. The redundancy and the information content of a band subset are restricted and enhanced by the correlation coefficient and the information divergence (ID), respectively. Subsequently, RRI combines these three indicators as the subset evaluation criterion and utilizes an immune clone selection algorithm to search for the desired band subset. Experimental results verify that the proposed RRI method can provide higher classification accuracy than the competitors and is robust to noisy bands.
- 30 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 19 (1545598X) , 1-5
A Band Selection Method With Masked Convolutional Autoencoder for Hyperspectral Image
Band selection (BS) is an effective means to solve the problems of spectral redundancy and Hughes phenomenon in hyperspectral images (HSIs). However, existing BS methods fail to consider the representativeness, redundancy, and information content of the selected bands simultaneously, and most of them lack consideration of the inherent nonlinear relationship between bands. To address these problems, we propose a novel unsupervised BS framework that can comprehensively consider band representativeness, redundancy, and information content (RRI) in this letter. The band representativeness is estimated by a convolutional autoencoder (AE), which can capture the inherent nonlinear relationship between the bands and leverage the spatial information of the HSI. The redundancy and the information content of a band subset are restricted and enhanced by the correlation coefficient and the information divergence (ID), respectively. Subsequently, RRI combines these three indicators as the subset evaluation criterion and utilizes an immune clone selection algorithm to search for the desired band subset. Experimental results verify that the proposed RRI method can provide higher classification accuracy than the competitors and is robust to noisy bands.
- Open Access
- 5 November 2021
- Published by Slovenian Association Informatika in Informatica
- Vol. 45 (7)
The effect of luminance contrast between sign and surrounding object on gaze behavior: A study in virtual metro station environment with rendered static/dynamic panorama
This paper investigated the effect of luminance contrast between sign and surrounding object on the gaze behavior of pedestrian, static or dynamic 360° panorama rendered in a virtual environment applied to simulate the wayfinding of pedestrians in the metro stations. Fifty-five participants observed the sign posters and the advertisement boards with distinct luminance contrasts (31 of them were in static levels, 24 of the rest were in dynamic levels) and were asked to point out the graphic or textual changes in the area after 30s. The eye tracker recorded ocular data, and glare perception was inquired by questionnaire. The result of T-test and Regression analysis revealed that luminance contrast was a saliency feature distinguishing visual targets and surrounding objects. The correlation between the value of luminance contrast and fixations, fixation durations on the sign is negative. Each increase in luminance contrast by one unit reduces the mean of fixations by 0.826, accompanied by a stronger feeling of glare, which indicated the strategic adaption of visual attention. The study contributed to our understanding of a new sight of lighting design in public traffic places and confirmed that lighting simulation in an immersive virtual environment can effectively analyzes visual perception.
- 5 November 2021
- Published by Slovenian Association Informatika in Informatica
- Vol. 45 (7)
Open AccessThe effect of luminance contrast between sign and surrounding object on gaze behavior: A study in virtual metro station environment with rendered static/dynamic panorama
This paper investigated the effect of luminance contrast between sign and surrounding object on the gaze behavior of pedestrian, static or dynamic 360° panorama rendered in a virtual environment applied to simulate the wayfinding of pedestrians in the metro stations. Fifty-five participants observed the sign posters and the advertisement boards with distinct luminance contrasts (31 of them were in static levels, 24 of the rest were in dynamic levels) and were asked to point out the graphic or textual changes in the area after 30s. The eye tracker recorded ocular data, and glare perception was inquired by questionnaire. The result of T-test and Regression analysis revealed that luminance contrast was a saliency feature distinguishing visual targets and surrounding objects. The correlation between the value of luminance contrast and fixations, fixation durations on the sign is negative. Each increase in luminance contrast by one unit reduces the mean of fixations by 0.826, accompanied by a stronger feeling of glare, which indicated the strategic adaption of visual attention. The study contributed to our understanding of a new sight of lighting design in public traffic places and confirmed that lighting simulation in an immersive virtual environment can effectively analyzes visual perception.
- Open Access
- 9 September 2021
- Published by MDPI AG in Remote Sensing
- Vol. 13 (18) , 3602
EBARec-BS: Effective Band Attention Reconstruction Network for Hyperspectral Imagery Band Selection
Hyperspectral band selection (BS) is an effective means to avoid the Hughes phenomenon and heavy computational burden in hyperspectral image processing. However, most of the existing BS methods fail to fully consider the interaction between spectral bands and cannot comprehensively consider the representativeness and redundancy of the selected band subset. To solve these problems, we propose an unsupervised effective band attention reconstruction framework for band selection (EBARec-BS) in this article. The framework utilizes the EBARec network to learn the representativeness of each band to the original band set and measures the redundancy between the bands by calculating the distance of each unselected band to the selected band subset. Subsequently, by designing an adaptive weight to balance the influence of the representativeness metric and redundancy metric on the band evaluation, a final band scoring function is obtained to select a band subset that well represents the original hyperspectral image and has low redundancy. Experiments on three well-known hyperspectral data sets indicate that compared with the existing BS methods, the proposed EBARec-BS is robust to noise bands and can effectively select the band subset with higher classification accuracy and less redundant information.
- 9 September 2021
- Published by MDPI AG in Remote Sensing
- Vol. 13 (18) , 3602
Open AccessEBARec-BS: Effective Band Attention Reconstruction Network for Hyperspectral Imagery Band Selection
Hyperspectral band selection (BS) is an effective means to avoid the Hughes phenomenon and heavy computational burden in hyperspectral image processing. However, most of the existing BS methods fail to fully consider the interaction between spectral bands and cannot comprehensively consider the representativeness and redundancy of the selected band subset. To solve these problems, we propose an unsupervised effective band attention reconstruction framework for band selection (EBARec-BS) in this article. The framework utilizes the EBARec network to learn the representativeness of each band to the original band set and measures the redundancy between the bands by calculating the distance of each unselected band to the selected band subset. Subsequently, by designing an adaptive weight to balance the influence of the representativeness metric and redundancy metric on the band evaluation, a final band scoring function is obtained to select a band subset that well represents the original hyperspectral image and has low redundancy. Experiments on three well-known hyperspectral data sets indicate that compared with the existing BS methods, the proposed EBARec-BS is robust to noise bands and can effectively select the band subset with higher classification accuracy and less redundant information.