16 papers
Evaluating Machine Learning Models for Post-Wildfire Debris-Flow Prediction
Quinn Ledingham, Zhengsen Xu, Yimin Zhu +6
Prediction of post-wildfire debris flows is critical for mitigating hazards to communities, infrastructure, and resources during intense rainfall in recently burned areas. However,…
A Novel Geographic Graph-Regulated Disentangling Mamba Model with Sparse Tokens for Enhanced Tree Species Classification from MODIS Time Series
Motasem Alkayid, Zhengsen Xu, Saeid Taleghanidoozdoozan +7
Tree species classification from Moderate Resolution Imaging Spectroradiometer (MODIS) time series is critical for environmental monitoring, yet challenging due to subtle inter-spe…
Defending against Patch-Based and Texture-Based Adversarial Attacks with Spectral Decomposition
Wei Zhang, Xinyu Chang, Xiao Li +2
Adversarial examples present significant challenges to the security of Deep Neural Network (DNN) applications. Specifically, there are patch-based and texture-based attacks that ar…
Unmixing-Guided Spatial-Spectral Mamba with Clustering Tokens for Hyperspectral Image Classification
Yimin Zhu, Lincoln Linlin Xu
Although hyperspectral image (HSI) classification is critical for supporting various environmental applications, it is a challenging task due to the spectral-mixture effect, the sp…
DSCSNet: A Dynamic Sparse Compression Sensing Network for Closely-Spaced Infrared Small Target Unmixing
Zhiyang Tang, Yiming Zhu, Ruimin Huang +4
Due to the limitations of optical lens focal length and detector resolution, distant clustered infrared small targets often appear as mixed spots. The Close Small Object Unmixing (…
mHC-HSI: Clustering-Guided Hyper-Connection Mamba for Hyperspectral Image Classification
Yimin Zhu, Zack Dewis, Quinn Ledingham +6
Recently, DeepSeek has invented the manifold-constrained hyper-connection (mHC) approach which has demonstrated significant improvements over the traditional residual connection in…
Clustering-Guided Spatial-Spectral Mamba for Hyperspectral Image Classification
Zack Dewis, Yimin Zhu, Zhengsen Xu +4
Although Mamba models greatly improve Hyperspectral Image (HSI) classification, they have critical challenges in terms defining efficient and adaptive token sequences for improve p…
White-Box mHC: Electromagnetic Spectrum-Aware and Interpretable Stream Interactions for Hyperspectral Image Classification
Yimin Zhu, Lincoln Linlin Xu, Zhengsen Xu +6
In hyperspectral image classification (HSIC), most deep learning models rely on opaque spectral-spatial feature mixing, limiting their interpretability and hindering understanding…
Trustworthy Data-Driven Wildfire Risk Prediction and Understanding in Western Canada
Zhengsen Xu, Lanying Wang, Sibo Cheng +12
In recent decades, the intensification of wildfire activity in western Canada has resulted in substantial socio-economic and environmental losses. Accurate wildfire risk prediction…
Diffusion Posterior Sampler for Hyperspectral Unmixing with Spectral Variability Modeling
Yimin Zhu, Lincoln Linlin Xu
Linear spectral mixture models (LMM) provide a concise form to disentangle the constituent materials (endmembers) and their corresponding proportions (abundance) in a single pixel.…
Multitask GLocal OBIA-Mamba for Sentinel-2 Landcover Mapping
Zack Dewis, Yimin Zhu, Zhengsen Xu +5
Although Sentinel-2 based land use and land cover (LULC) classification is critical for various environmental monitoring applications, it is a very difficult task due to some key d…
Knowledge-Aware Mamba for Joint Change Detection and Classification from MODIS Times Series
Zhengsen Xu, Yimin Zhu, Zack Dewis +4
Although change detection using MODIS time series is critical for environmental monitoring, it is a highly challenging task due to key MODIS difficulties, e.g., mixed pixels, spati…
Spatial-Temporal-Spectral Mamba with Sparse Deformable Token Sequence for Enhanced MODIS Time Series Classification
Zack Dewis, Zhengsen Xu, Yimin Zhu +3
Although MODIS time series data are critical for supporting dynamic, large-scale land cover land use classification, it is a challenging task to capture the subtle class signature…
Sparse Deformable Mamba for Hyperspectral Image Classification
Lincoln Linlin Xu, Yimin Zhu, Zack Dewis +4
Although Mamba models significantly improve hyperspectral image (HSI) classification, one critical challenge is the difficulty in building the sequence of Mamba tokens efficiently.…
Spatial-Spectral Diffusion Contrastive Representation Network for Hyperspectral Image Classification
Yimin Zhu, Linlin Xu
Although efficient extraction of discriminative spatial-spectral features is critical for hyperspectral images classification (HSIC), it is difficult to achieve these features due…
Language-Informed Hyperspectral Image Synthesis for Imbalanced-Small Sample Classification via Semi-Supervised Conditional Diffusion Model
Yimin Zhu, Lincoln Linlin Xu
Data augmentation effectively addresses the imbalanced-small sample data (ISSD) problem in hyperspectral image classification (HSIC). While most methodologies extend features in th…