Constructing a Large-Scale Landslide Database Across Heterogeneous Environments Using Task-Specific Model Updates
نویسندگان
چکیده
Preparation and mitigation efforts for widespread landslide hazards can be aided by a large-scale, well-labeled inventory with high location accuracy. Recent smallscale studies pixel-wise labeling of potential areas in remotely-sensed images using deep learning (DL) showed but were based on data from very small, homogeneous regions unproven model transferability. In this paper we consider more realistic practical setting large-scale heterogeneous collection DL-based labeling. setting, remotely sensed are collected sequentially temporal batches, where each batch focuses particular ecoregion, different batches focus ecoregions distinct landscape characteristics. For such scenario, study the following questions: (1) How well do DL models trained perform when they transferred to ecoregions, (2) Does increasing spatial coverage improve performance given ecoregion (even extra not come ecoregion), (3) Can pixel incrementally updated new data, without access old losing (so that researchers share obtained proprietary datasets)' We address these questions extending Learning Forgetting framework, which is used incremental training image classification models, semantic segmentation (e.g., identifying all pixels an image). call resulting extension Task-Specific Model Updates (TSMU). TSMU framework consists encoder shared capture similarities between them, ecoregion-specific decoders nuances ecoregion. This continually threestage procedure addition having revisit them.
منابع مشابه
A hierarchical model for processing noisy and partial information in large-scale real-time task environments
In this paper we introduce the Incremental Distributed Dispatcher Manager (IDDM) that is designed to handle control problems with large numbers of tasks and cooperative agents where only partial and noisy information is available. The IDDM is a modification of the DDM model that was developed to solve similar problems but in environments where accurate information is available. There were a num...
متن کاملOnline Task Allocation in Client-Server Large Scale Heterogeneous Platforms
In this paper, we consider the problem of the online allocation of a very large number of identical tasks on a masterslave platform. Initially, several masters hold or generate tasks that are transfered and processed by slave nodes. The goal is to maximize the overall throughput achieved using this platform, i.e., the (fractional) number of tasks that can be processed within one time unit. We m...
متن کاملUnsupervised Category Discovery via Looped Deep Pseudo-Task Optimization Using a Large Scale Radiology Image Database
Obtaining semantic labels on a large scale radiology image database (215,786 key images from 61,845 unique patients) is a prerequisite yet bottleneck to train highly effective deep convolutional neural network (CNN) models for image recognition. Nevertheless, conventional methods for collecting image labels (e.g., Google search followed by crowd-sourcing) are not applicable due to the formidabl...
متن کاملA Practical Desalinization Model for Large Scale Application
Salinity of soil and water is the most important agricultural hazard in arid and semi-aridregions. In saline soils, yield production directly influences by soluble salts in the root zone aswell as by shallow water table depth. The first step for reclamation of such soils is reducingsalinity to optimum level by leaching. The objective of this study was to develop a practicalmodel to estimate wat...
متن کاملSpecifying Database Updates Using A Subschema
The notion of a subschema, as a formal and abstract definition of data, constraints, and database update activities that are needed to make a transaction program, is introduced in the paper. Subschema is a component of a transaction program specification. It is designed using a user request and an existing relational database schema. The principles of a database update using subschema concepts ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
سال: 2022
ISSN: ['2151-1535', '1939-1404']
DOI: https://doi.org/10.1109/jstars.2022.3177025