Sequential Feature Selection for Efficient Landslide Segmentation from Multi-Spectral Data
School of Computer Science(计算机科学学院);Informatics Cardiff University(卡迪夫大学信息学)
Arsalaan Ahmad, Oktay Karakus, Paul L. Rosin
备注:
In Process of Submission to Frontiers in Remote Sensing. Keywords: landslide segmentation, multispectral remote sensing, feature selection, explainability, Landslide4Sense
Landslide detection from satellite imagery has advanced through deep learning, yet most models rely on large, highly correlated spectral-topographic inputs whose contributions remain poorly understood. The question of which channels are actually necessary has received surprisingly little attention. This matters: redundant or correlated inputs obscure physical interpretability, inflate computational overhead, and can actively degrade model performance through the Hughes Phenomenon. We present a systematic, explainable channel-selection framework for the Landslide4Sense benchmark, combining Sentinel-2 multispectral and ALOS PALSAR terrain data with 16 engineered spectral and structural indices. Rather than relying on conventional single-band drop tests, which evaluate channels in isolation and miss interaction effects, we apply Sequential Forward Floating Selection (SFFS) to iteratively build and prune a candidate feature pool using a lightweight U-Net++ proxy model. Beyond identifying a compact 8-channel subset that matches or exceeds the segmentation F1 of configurations using up to 30 channels, we use the selection process itself to interrogate which spectral and topographic features landslide models genuinely rely on, and what this reveals about the physical cues driving their predictions. We argue that SFFS represents a principled feature selection approach to input design in Earth observation, in contrast to the prevailing practice of appending every available band and hoping the model learns what to ignore.
An Iterative Classification and Semantic Segmentation Network for Old Landslide Detection Using High-Resolution Remote Sensing Images
Beijing University of Posts and Telecommunications(北京邮电大学);Beijing Institute of Technology(北京理工大学);China Aero Geophysical Survey and Remote Sensing Center for Natural Resources(中国自然资源航空物探遥感中心);La Trobe University(乐卓博大学)
RMAU-NET: A Residual-Multihead-Attention U-Net Architecture for Landslide Segmentation and Detection from Remote Sensing Images
Van Lang University(范兰大学);Austrian Institute of Technology(奥地利技术研究院);Troyes University(特鲁瓦大学);HCM University of Technology(胡志明技术大学);Ton Duc Thang University(-ton Duc Thang大学)
本文提出了一种基于残差多头注意力 U-Net 架构的端到端深度学习模型 RMAU-NET,利用遥感图像进行滑坡检测与分割,在多个基准数据集上取得了优异的 F1 和 mIoU 分数,证明了其在实际滑坡观测系统中的应用潜力。
Landslide Detection and Segmentation Using Remote Sensing Images and Deep Neural Network
Austrian Institute of Technology(奥地利技术研究院);GeoSphere Austria(奥地利地球物理、气象和地球物理研究所);University of Natural Resources and Life Sciences, Vienna(维也纳自然资源与生命科学大学)
Kernel Clustering with Sigmoid-based Regularization for Efficient Segmentation of Sequential Data
Hanoi University of Science and Technology(河内理工大学);The Graduate University for Advanced Studies, SOKENDAI(综合研究大学院大学(SOKENDAI));National Institute of Informatics(国立信息学研究所)
MMLSv2: A Multimodal Dataset for Martian Landslide Detection in Remote Sensing Imagery
Fairfield University(费尔菲尔德大学);Michigan Technological University(密歇根技术大学);Computer Vision Center(计算机视觉中心);Universitat Autònoma de Barcelona(巴塞罗那自治大学);ESPOL Polytechnic University(ESPOL多科大学);University of Kerala(喀拉拉大学);University of Mississippi(密西西比大学)
Feature Selection based on Machine Learning in MRIs for Hippocampal Segmentation
Istituto Nazionale di Fisica Nucleare(意大利国家核物理研究所);Università degli Studi di Bari(巴里大学);INAF - Astronomical Observatory of Capodimonte(意大利国家天体物理研究所-卡波迪蒙特天文台);Università degli Studi di Genova(热那亚大学);Università degli Studi di Napoli Federico II(那不勒斯费德里克二世大学);Istituto di Studi sui Sistemi Intelligenti per l’Automazione, CNR(意大利国家研究委员会智能系统与自动化研究所)
Stochastic Sequential Neural Networks with Structured Inference
University of Electronic Science and Technology of China(电子科技大学);SMILE Lab & Yingcai Honors College(SMILE实验室与英才实验学院);SMILE Lab & Big Data Research Center(SMILE实验室与大数据研究中心);School of Computer Science and Engineering(计算机科学与工程学院)
Investigation on the use of Hidden-Markov Models in automatic transcription of music
ENSTA Bretagne(布列塔尼国立高等先进技术学校);Université Européenne de Bretagne(布列塔尼欧洲大学);Université Paris Descartes(巴黎笛卡尔大学)
隐马尔可夫模型(Hidden Markov Models,简称HMM)是一种普遍存在的对时间序列数据建模的工具,已被广泛应用于自动音乐转录(Automatic Music Transcription,简称AMT)的两个主要任务:音符分割,即在多音高估计之后识别所演奏的音符;以及顺序后处理,即使用训练数据校正音符分割。在本文中,我们采用多基音周期估计方法称为概率潜在成分分析(PLCA),并开发AMT系统集成不同的HMM为基础的模块在这个框架。对于笔记分割,我们使用两种不同的双状态on/o?阻碍,包括持续时间建模的高阶阻碍。对于顺序后处理,我们专注于复调和声过渡的音乐学建模,使用一阶和二阶Hertons,其状态通过候选音符混合物定义。这些不同的PLCA加HMM系统进行了评估比较两个不同的乐器曲目,即钢琴(使用MAPS数据库)和marovany齐特琴。我们的研究结果表明,使用的HALGOR可以带来显着的改善转录结果,这取决于仪器的剧目。