Chuiyi Deng

Chuiyi Deng

Auto-generated profile, based on publicly available information

Chuiyi Deng

College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 August 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
CDChuiyi Deng
Chuiyi Deng
ZZZhuoyi Zhao
Zhuoyi Zhao
Xiang XuXiang Xu
Xiang Xu
YXYixin Xia
Yixin Xia
JLJunwei Li
Junwei Li
Antonio PlazaAntonio Plaza
Antonio Plaza
Infrared small target detection (IRSTD) has progressed significantly in spatial-domain learning. However, single-frame images’ limited spatial semantics impair discrimination between targets and similar noise while complicating integrity detection of large-scale target. To address these, we propose Global Spatial-Frequency Attention Network (GSFANet), which enhances the distribution difference between targets and noise from a frequency-domain perspective while preserving spatial information integrity. The core innovations consist of three modules: 1) Parametric Wavelet Downsampling (PWD), preserving small target details during frequency refinement to prevent feature fragmentation; 2) Hierarchical Gated Kernel Attention (HGKA), capturing cross-level frequency relationships through Cross-channel Kernel Attention (C2K) and maintaining spatial coherence via Cross-spatial Gate Attention (CSG), effectively bridging semantic gaps across layers; 3) Adaptive Frequency-Decoupled Fusion (AdaFD), dynamically fusing target-associated frequency components while suppressing noise. We further develop AdaFL Loss to balance multi-scale target gradients and stabilize training. Experiments on three benchmark datasets demonstrate GSFANet’s superior detection performance and enhanced segmentation robustness in complex scenarios compared to state-of-the-art methods. Our code will be made public at https://github.com/dengfa02/GSFANet_IRSTD.

7 August 2023 in Ocean Engineering
Verified
Journal Article
Closed access
CDChuiyi Deng
Chuiyi Deng
SWShuangxin Wang
Shuangxin Wang
JLJingyi Liu
Jingyi Liu
HLHongrui Li
Hongrui Li
BCBoce Chu
Boce Chu
JZJin Zhu
Jin Zhu

26 January 2026 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
CDChuiyi Deng
Chuiyi Deng
YGYanyin Guo
Yanyin Guo
Xiang XuXiang Xu
Xiang Xu
ZZZhuoyi Zhao
Zhuoyi Zhao
YXYixin Xia
Yixin Xia
Antonio PlazaAntonio Plaza
Antonio Plaza
Motion Infrared Small Target Detection (MIRSTD) leverages multi-frame temporal dependencies to improve detection robustness. However, existing methods have difficulty modeling global consistency and achieving precise alignment in complex motion and large displacement scenarios, leading to dispersed target representations and higher error rates. To address these challenges, we propose Dynamic Query Aligner (DQAligner), which introduces global random large-displacement augmentation and a cross-scale bidirectional shared attention mechanism to enhance inter-frame consistency. A dynamic receptive field pyramid deformable convolution decomposes complex multi-scale motions, enabling precise target alignment. Furthermore, class query memory serves as the generalized residual form of deformable convolution, which iteratively learns dynamic query representations to facilitate global target localization within each frame and maintain semantic consistency across frames. DQAligner achieves a paradigm shift from rigid alignment to flexible matching, and significantly boosts detection performance in large displacement and dynamic scenarios. Experiments on extensive stationary and moving platform datasets show that DQAligner outperforms existing methods, especially under complex motion and low signal-noise-rate conditions. Code will be available at https://github.com/dengfa02/DQAligner_MIRSTD.

20 January 2026 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
ZZZhuoyi Zhao
Zhuoyi Zhao
Xiang XuXiang Xu
Xiang Xu
CDChuiyi Deng
Chuiyi Deng
JLJunwei Li
Junwei Li
Antonio PlazaAntonio Plaza
Antonio Plaza
Hyperspectral image (HSI) classification is a critical task in remote sensing. Recently, deep learning (DL) methods, particularly state space models (SSMs) like Mamba, have garnered significant attention due to their linear computational complexity in handling long sequences. However, processing the rich yet redundant spectral bands in HSIs remains challenging for these approaches, often resulting in models with excessive parameters. Moreover, existing DL-based methods frequently overlook explicit cross-channel dependencies. This limitation hinders their ability to effectively aggregate relevant information from redundant spectral bands. Additionally, the heavy reliance of DL-based models on extensive training data conflicts with the scarcity of labeled samples in HSI scenarios. This necessitates the incorporation of prior knowledge to mitigate data limitations. To address these challenges, we propose SliMamba, a lightweight Convolution-Mamba architecture for HSI classification (HSIC). SliMamba introduces two key components: spectral selection convolution (SSC) and overlapped-centering mamba (OC-Mamba). SSC swaps dimensions between spectral and spatial axes while preserving the original spectral information. It then utilizes a small set of convolutional kernels to learn spectral weights within the receptive field, thereby achieving cross-channel feature representation. OC-Mamba integrates prior knowledge of the center pixel with local feature enhancement. It combines one-pixel overlapped SSM (O-SSM) and centering SSM (C-SSM) to extract global–local and spectral–spatial features from HSI feature maps. Extensive evaluations on four benchmark datasets demonstrate that SliMamba consistently outperforms state-of-the-art methods in classification accuracy while significantly reducing model complexity. The source code is available at https://github.com/flyzzie/SliMamba

19 March 2025 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
CDChuiyi Deng
Chuiyi Deng
SWShuangxin Wang
Shuangxin Wang
JLJunwei Li
Junwei Li
JLJingyi Liu
Jingyi Liu
HLHongrui Li
Hongrui Li
MSMingli Song
Mingli Song
The Automatic Identification System (AIS) extends traditional measurement methods, enabling real-time situational awareness at intersections. However, most methods rely on extensive historical data from multiple intersections, which conflicts with the limited sensing range of onboard measurement. Moreover, state-of-the-art (SOTA) models suffer from error accumulation, high prediction uncertainty, and inadequate global variate modeling, limiting trend awareness and generalization across measurement scales. To overcome these, we propose iTentformer, an encoder-only model focusing on short-term vessel behavior at intersection waterways. Key innovations include: (1) a variate-centered encoder to capture distribution differences before intersections, and (2) integration of the predicted course as a trend prior, highlighting pattern changes before intersections. These components are optimized through variate representation fusion and multi-task learning. Extensive experiments show that iTentformer reduces ADE by 35% and FDE by 30% compared to SOTA Transformer-based models, improving trajectory abstraction and reducing estimation uncertainty through strong trend awareness. Notably, vessel navigational status at intersections significantly impacts measurement distribution. Additionally, its improved RUL prediction highlights its potential for broader measurement applications. The code is available at github.com/dengfa02/iTentformer.

26 March 2026 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
ZZZhuoyi Zhao
Zhuoyi Zhao
Xiang XuXiang Xu
Xiang Xu
CDChuiyi Deng
Chuiyi Deng
YGYanyin Guo
Yanyin Guo
JLJunwei Li
Junwei Li
Antonio PlazaAntonio Plaza
Antonio Plaza
In recent years, deep learning (DL) has achieved remarkable progress in hyperspectral unmixing (HU) owing to its powerful feature extraction and modeling capabilities. However, the majority of existing DL-based methods operate primarily in the spatial-spectral domain and overlook the rich structural information embedded in frequency-domain representations, particularly in the Fourier domain. Consequently, they often struggle to effectively address challenges such as spectral variability and random noise. In the Fourier domain, low- and high-frequency components can be flexibly decomposed, enabling targeted feature extraction that enhances unmixing robustness by emphasizing discriminative spectral structures while suppressing noise. Motivated by these advantages, we introduce the Frequency-Adaptive Convolutional-Mamba (FACM), a novel end-to-end blind HU framework. To our knowledge, this is the first work to unify the entire pipeline, including abundance estimation, endmember extraction, and the loss function, completely within the Fourier domain. In the abundance estimation branch, FACM captures complementary local and global spectral-spatial cues via frequency-adaptive feature modeling in the Fourier domain. In the endmember extraction branch, FACM generates accurate, initialization-free candidate endmembers by weighting learnable spectral embeddings with frequency-specific coefficients. Moreover, a frequency-domain loss jointly constrains the reconstruction from magnitude and phase perspectives. Extensive experiments on simulated and realworld benchmarks demonstrate that FACM consistently outperforms state-of-the-art methods in both endmember extraction and abundance estimation accuracy. The source code is available at https://github.com/flyzzie/FACM.