Huaixi Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Huaixi Zhu has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Ran Zhou
School of Physics and Photoelectric Engineering, Key Laboratory of Gravitational Wave Precision Measurement of Zhejiang Province, Taiji Laboratory for Gravitational Wave Universe, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, China
4 shared publications - Tong Zhu
School of Physics and Photoelectric Engineering, Key Laboratory of Gravitational Wave Precision Measurement of Zhejiang Province, Taiji Laboratory for Gravitational Wave Universe, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, China
4 shared publications - Yikun Wang
School of Physics and Photoelectric Engineering, Key Laboratory of Gravitational Wave Precision Measurement of Zhejiang Province, Taiji Laboratory for Gravitational Wave Universe, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, China
4 shared publications - Fang Gao
School of Physics and Photoelectric Engineering, Key Laboratory of Gravitational Wave Precision Measurement of Zhejiang Province, Taiji Laboratory for Gravitational Wave Universe, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, China
3 shared publications - Jiaoyang Xing
Key Laboratory of Gravitational Wave Precision Measurement of Zhejiang Province, Taiji Laboratory for Gravitational Wave Universe, Hangzhou Institute for Advanced Study, School of Physics and Photoelectric Engineering, University of Chinese Academy of Sciences, Hangzhou 310024, China
3 shared publications - Jingyan Fan
Key Laboratory of Gravitational Wave Precision Measurement of Zhejiang Province, Taiji Laboratory for Gravitational Wave Universe, Hangzhou Institute for Advanced Study, School of Physics and Photoelectric Engineering, University of Chinese Academy of Sciences, Hangzhou 310024, China
3 shared publications
Latest Publications
- Open Access
- 23 August 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (17) , 2855
Reliability-Aware Adaptive Band Gating with Domain Expansion for Cross-Scene Hyperspectral Band Selection
Cross-scene hyperspectral band selection must reduce spectral redundancy while retaining channels that remain useful beyond the source scene. We propose Adaptive Band Gating (ABG), a source-only selector that combines frequency-domain decoupling enhancement, global and sample-specific gating, source-side spectral, spatial, morphology-inspired, and sensor-noise perturbations, and a dual-head evaluator. The selector is trained with source data and frozen before downstream evaluation. Selected bands are assessed with a radial-basis-function support vector machine on Pavia Center and HyRANK under fixed band budgets and target-label fractions from 0% to 10%. At 5% target labels, 15 selected bands achieve 96.05% overall accuracy on Pavia Center, compared with 95.41% using all 102 bands; 20 selected bands achieve 81.49% on HyRANK, compared with 79.20% using all 176 bands. Across evaluated band budgets, ABG is comparable to XGBS on Pavia Center and provides stronger results on HyRANK. Ablation experiments show that adaptive gating, frequency-domain enhancement, and source-side expansion each contribute to performance. Together, these results demonstrate that ABG learns compact and traceable original-band subsets with strong downstream transfer utility across the evaluated cross-scene settings.
- 23 August 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (17) , 2855
Open AccessReliability-Aware Adaptive Band Gating with Domain Expansion for Cross-Scene Hyperspectral Band Selection
Cross-scene hyperspectral band selection must reduce spectral redundancy while retaining channels that remain useful beyond the source scene. We propose Adaptive Band Gating (ABG), a source-only selector that combines frequency-domain decoupling enhancement, global and sample-specific gating, source-side spectral, spatial, morphology-inspired, and sensor-noise perturbations, and a dual-head evaluator. The selector is trained with source data and frozen before downstream evaluation. Selected bands are assessed with a radial-basis-function support vector machine on Pavia Center and HyRANK under fixed band budgets and target-label fractions from 0% to 10%. At 5% target labels, 15 selected bands achieve 96.05% overall accuracy on Pavia Center, compared with 95.41% using all 102 bands; 20 selected bands achieve 81.49% on HyRANK, compared with 79.20% using all 176 bands. Across evaluated band budgets, ABG is comparable to XGBS on Pavia Center and provides stronger results on HyRANK. Ablation experiments show that adaptive gating, frequency-domain enhancement, and source-side expansion each contribute to performance. Together, these results demonstrate that ABG learns compact and traceable original-band subsets with strong downstream transfer utility across the evaluated cross-scene settings.
- Open Access
- 7 August 2026
- Published by MDPI AG in Electronics
- Vol. 15 (16) , 3518
RSSMamba: A Region Spectral-Spatial Mamba Network with Bidirectional Spiral Scanning and Cross-Attention for Hyperspectral Image Classification
Hyperspectral image (HSI) classification aims to assign a land cover label to each pixel by jointly exploiting spectral signatures and spatial contextual information. Recently, Mamba-based state-space models have shown potential for long-range dependency modeling with improved efficiency compared with Transformer-based architectures. However, directly applying standard Mamba structures to patch-based HSI classification still faces three major limitations: Noisy pixel-level tokens may disturb state-space propagation, conventional scanning paths are not well aligned with central-pixel prediction, and fine-grained spectral signatures may be weakened in deep feature representations. To address these issues, this paper proposes a Region Spectral–Spatial Mamba network with Bidirectional Spiral Scanning and Cross-Attention, termed RSSMamba. Specifically, a Dynamic Spatial–Spectral Saliency Tokenization (DSST) module is first designed to suppress redundant spatial–spectral responses and generate semantically consistent regional tokens. Then, a Bidirectional Spiral Selective Scanning (B3S) mechanism serializes the feature map along clockwise and counter-clockwise spiral paths, enabling contextual information to be aggregated toward the central target pixel. Finally, a Spectral Cross-Attention (SCA) module injects the shallow central spectral feature into the deep center-oriented descriptor through a lightweight, head-partitioned cross-layer fusion, thereby alleviating spectral feature attenuation. Under the adopted random pixel-wise evaluation protocol, experiments on four benchmark HSI datasets, including Indian Pines, WHU-HI-Longkou, Pavia University, and WHU-HI-HanChuan, yield competitive aggregate results relative to the included CNN-, Transformer-, and Mamba-based baselines. In the ten-run reporting format, RSSMamba obtains OA values of %, %, %, and % on the four datasets, respectively. It reports 0.33M parameters and 8.84G FLOPs on Indian Pines.- 7 August 2026
- Published by MDPI AG in Electronics
- Vol. 15 (16) , 3518
Open AccessRSSMamba: A Region Spectral-Spatial Mamba Network with Bidirectional Spiral Scanning and Cross-Attention for Hyperspectral Image Classification
Hyperspectral image (HSI) classification aims to assign a land cover label to each pixel by jointly exploiting spectral signatures and spatial contextual information. Recently, Mamba-based state-space models have shown potential for long-range dependency modeling with improved efficiency compared with Transformer-based architectures. However, directly applying standard Mamba structures to patch-based HSI classification still faces three major limitations: Noisy pixel-level tokens may disturb state-space propagation, conventional scanning paths are not well aligned with central-pixel prediction, and fine-grained spectral signatures may be weakened in deep feature representations. To address these issues, this paper proposes a Region Spectral–Spatial Mamba network with Bidirectional Spiral Scanning and Cross-Attention, termed RSSMamba. Specifically, a Dynamic Spatial–Spectral Saliency Tokenization (DSST) module is first designed to suppress redundant spatial–spectral responses and generate semantically consistent regional tokens. Then, a Bidirectional Spiral Selective Scanning (B3S) mechanism serializes the feature map along clockwise and counter-clockwise spiral paths, enabling contextual information to be aggregated toward the central target pixel. Finally, a Spectral Cross-Attention (SCA) module injects the shallow central spectral feature into the deep center-oriented descriptor through a lightweight, head-partitioned cross-layer fusion, thereby alleviating spectral feature attenuation. Under the adopted random pixel-wise evaluation protocol, experiments on four benchmark HSI datasets, including Indian Pines, WHU-HI-Longkou, Pavia University, and WHU-HI-HanChuan, yield competitive aggregate results relative to the included CNN-, Transformer-, and Mamba-based baselines. In the ten-run reporting format, RSSMamba obtains OA values of %, %, %, and % on the four datasets, respectively. It reports 0.33M parameters and 8.84G FLOPs on Indian Pines. - Open Access
- 9 February 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (4) , 1719
Lightweight CNN-CEM for Efficient Hyperspectral Target Detection on Resource-Constrained Edge Devices
Efficient target detection in hyperspectral images faces significant deployment challenges on resource-constrained edge platforms due to the large data volume and high computational complexity of detection algorithms. This paper proposes a CEM target detection method based on 1D-CNN feature dimensionality reduction. A lightweight 1D-CNN reduces spectral dimensions from L bands to 16 features, decreasing the core matrix inversion complexity from to . Unlike PCA-based dimensionality reduction requiring online eigenvalue decomposition, the proposed approach employs fixed pre-trained weights with simple convolution operations, enabling high parallelizability for FPGA implementation. A Zynq-based PS + PL collaborative acceleration scheme is designed, deploying CNN on the PL side through RTL implementation and CEM on the PS side using double-precision floating-point computation. Experimental validation on multiple hyperspectral datasets demonstrates that the proposed method achieves an AUC of 0.9953 with less than 1% difference compared to traditional CEM, processes 40,000 pixels in approximately 10.8 s, and consumes only 2.067 W, making it suitable for power-sensitive edge applications such as UAV reconnaissance and satellite on-board processing. The system achieves a processing rate of 3704 pixels/s.- 9 February 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (4) , 1719
Open AccessLightweight CNN-CEM for Efficient Hyperspectral Target Detection on Resource-Constrained Edge Devices
Efficient target detection in hyperspectral images faces significant deployment challenges on resource-constrained edge platforms due to the large data volume and high computational complexity of detection algorithms. This paper proposes a CEM target detection method based on 1D-CNN feature dimensionality reduction. A lightweight 1D-CNN reduces spectral dimensions from L bands to 16 features, decreasing the core matrix inversion complexity from to . Unlike PCA-based dimensionality reduction requiring online eigenvalue decomposition, the proposed approach employs fixed pre-trained weights with simple convolution operations, enabling high parallelizability for FPGA implementation. A Zynq-based PS + PL collaborative acceleration scheme is designed, deploying CNN on the PL side through RTL implementation and CEM on the PS side using double-precision floating-point computation. Experimental validation on multiple hyperspectral datasets demonstrates that the proposed method achieves an AUC of 0.9953 with less than 1% difference compared to traditional CEM, processes 40,000 pixels in approximately 10.8 s, and consumes only 2.067 W, making it suitable for power-sensitive edge applications such as UAV reconnaissance and satellite on-board processing. The system achieves a processing rate of 3704 pixels/s. - Open Access
- 12 July 2025
- Published by MDPI AG in Electronics
- Vol. 14 (14) , 2805
A Deep-Learning Framework with Multi-Feature Fusion and Attention Mechanism for Classification of Chinese Traditional Instruments
Chinese traditional instruments are diverse and encompass a rich variety of timbres and rhythms, presenting considerable research potential. This work proposed a deep-learning framework for the automated classification of Chinese traditional instruments, addressing the challenges of acoustic diversity and cultural preservation. By integrating two datasets, CTIS and ChMusic, we constructed a combined dataset comprising four instrument families: wind, percussion, plucked string, and bowed string. Three time-frequency features, namely MFCC, CQT, and Chroma, were extracted to capture diverse sound information. A convolutional neural network architecture was designed, incorporating 3-channel spectrogram feature stacking and a hybrid channel–spatial attention mechanism to enhance the extraction of critical frequency bands and feature weights. Experimental results demonstrated that the feature-fusion method improved classification performance compared to a single feature as input. Meanwhile, the attention mechanism further boosted test accuracy to 98.79%, outperforming baseline models by 2.8% and achieving superior F1 scores and recall compared to classical architectures. Ablation study confirmed the contribution of attention mechanisms. This work validates the efficacy of deep learning in preserving intangible cultural heritage through precise analysis, offering a feasible methodology for the classification of Chinese traditional instruments.
- 12 July 2025
- Published by MDPI AG in Electronics
- Vol. 14 (14) , 2805
Open AccessA Deep-Learning Framework with Multi-Feature Fusion and Attention Mechanism for Classification of Chinese Traditional Instruments
Chinese traditional instruments are diverse and encompass a rich variety of timbres and rhythms, presenting considerable research potential. This work proposed a deep-learning framework for the automated classification of Chinese traditional instruments, addressing the challenges of acoustic diversity and cultural preservation. By integrating two datasets, CTIS and ChMusic, we constructed a combined dataset comprising four instrument families: wind, percussion, plucked string, and bowed string. Three time-frequency features, namely MFCC, CQT, and Chroma, were extracted to capture diverse sound information. A convolutional neural network architecture was designed, incorporating 3-channel spectrogram feature stacking and a hybrid channel–spatial attention mechanism to enhance the extraction of critical frequency bands and feature weights. Experimental results demonstrated that the feature-fusion method improved classification performance compared to a single feature as input. Meanwhile, the attention mechanism further boosted test accuracy to 98.79%, outperforming baseline models by 2.8% and achieving superior F1 scores and recall compared to classical architectures. Ablation study confirmed the contribution of attention mechanisms. This work validates the efficacy of deep learning in preserving intangible cultural heritage through precise analysis, offering a feasible methodology for the classification of Chinese traditional instruments.