Hard Region-Aware Network (HRANet) for Improved Change Detection in Remote Sensing Images
This paper introduces HRANet, a novel deep learning model for change detection in remote sensing images, which leverages hard region mining and cross-layer knowledge distillation to enhance accuracy, particularly in challenging areas like object boundaries and regions susceptible to background clutter.
Asymptotically Optimal Change Detection Using the Log-Partition Approximation Cumulative Sum (LPA-CUSUM) Algorithm for Unnormalized Pre- and Post-Change Distributions
The LPA-CUSUM algorithm offers an asymptotically optimal solution for change detection when only unnormalized pre- and post-change distributions are available, leveraging thermodynamic integration to estimate the log-ratio of normalizing constants and achieving performance comparable to the standard CUSUM algorithm with sufficient sample size.
ChangeMamba: Efficient Spatio-Temporal Modeling for Remote Sensing Change Detection
The ChangeMamba architecture, based on the Mamba state space model, can efficiently model the global spatial context and spatio-temporal relationships to achieve accurate and efficient change detection in remote sensing images.
Body Decouple VHR Remote Sensing Image Change Detection Method
The author proposes the BD-MSA model to address challenges in remote sensing image change detection, focusing on global and local feature information aggregation and decoupling the change region's center from its edges.
© 2024 by Linnk AI