Transfer learning for hierarchical Conditional Random Fields for the classification of urban aerial and satellite images

用于城市航空和卫星图像分类的分层条件随机场的迁移学习

• 批准号: 246463617
• 负责人: Professor Dr.-Ing. Christian Heipke
• 金额: --
• 依托单位: Institut für Photogrammetrie und GeoInformation (IPI)
• 依托单位国家: 德国
• 项目类别: Research Grants
• 财政年份: 2013
• 资助国家: 德国
• 起止时间: 2012-12-31 至 2016-12-31
• 项目状态: 已结题
• 来源: https://gepris.dfg.de/gepris/projekt/246463617?language=en
• 关键词: Transfer; learning; hierarchical; Conditional; Random

It is the goal of the proposed project to develop a methodology for the supervised context-based classification of aerial and high-resolution satellite images of urban areas. The main scientific contribution is the development and application of methods for transfer learning for determining the parameters of the classification model in order to reduce the amount of training data required for such a model. In order to overcome problems of methods based on local context only, a hierarchical model is proposed. The classification is based on a digital surface model and a true orthophoto, the mathematical framework is provided by Conditional Random Fields (CRF). Recent work on CRF-based classification has shown that simple models of local context may lead to over-smoothing of the results. More complex models can lead to better results, but they require a considerably larger amount of training data. Furthermore, CRF are known to have problems in modelling long-range interactions between objects in a scene. In order to tackle these problems, we suggest a new CRF-based classification technique using more complex context models than comparable methods. In order to reduce the amount of training data required for learning the parameters of these models, it is our goal to develop models that are suitable for transfer learning, so that training data acquired at another time and/or for another place can be transferred to a new scene to be classified. The suggested project constitutes the first application of the principles of transfer learning in the context of graph-based classification methods in image analysis. Furthermore, in order to be able to model long-range interactions in the probabilistic model with a realistic computational effort, scale space is considered explicitly by building a hierarchical model. The new methodology is evaluated on real data with a reference that was generated manually. The methodology developed in both projects, which deal with different aspects of transfer learning, will be exchanged and compared.

拟议项目的目标是制定一种方法，对城市地区的航空和高分辨率卫星图像进行有监督的基于上下文的分类。主要的科学贡献是开发和应用迁移学习方法来确定分类模型的参数，以减少这种模型所需的训练数据量。为了克服仅基于局部上下文的方法存在的问题，提出了一种分层模型。该分类基于数字曲面模型和真正射影像，数学框架由条件随机场（CRF）提供。最近对基于crf的分类的研究表明，简单的局部上下文模型可能导致结果的过度平滑。更复杂的模型可以产生更好的结果，但它们需要相当多的训练数据。此外，已知CRF在模拟场景中物体之间的远程交互方面存在问题。为了解决这些问题，我们提出了一种新的基于crf的分类技术，该技术使用比可比方法更复杂的上下文模型。为了减少学习这些模型参数所需的训练数据量，我们的目标是开发适合迁移学习的模型，这样在另一个时间和/或另一个地方获得的训练数据就可以转移到一个新的场景中进行分类。建议的项目构成了迁移学习原理在图像分析中基于图的分类方法背景下的第一个应用。此外，为了能够以实际的计算量在概率模型中模拟远程相互作用，通过建立层次模型明确地考虑了尺度空间。新方法在实际数据上进行了评估，并参考了人工生成的参考数据。这两个研究迁移学习的不同方面的项目所开发的方法将进行交流和比较。

项目成果

A COMPARISON OF TWO STRATEGIES FOR AVOIDING NEGATIVE TRANSFER IN DOMAIN ADAPTATION BASED ON LOGISTIC REGRESSION

基于逻辑回归的域适应中两种避免负迁移策略的比较

• DOI: 10.5194/isprs-archives-xlii-2-845-2018
• 发表时间: 2018
• 期刊: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
• 作者: Rottensteiner;Ostermann;Heipke
• 通讯作者: Heipke

TRANSFER LEARNING BASED ON LOGISTIC REGRESSION

• DOI: 10.5194/isprsarchives-xl-3-w3-145-2015
• 发表时间: 2015-08
• 期刊: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
• 作者: A. Paul;F. Rottensteiner;C. Heipke

ITERATIVE RE-WEIGHTED INSTANCE TRANSFER FOR DOMAIN ADAPTATION

• DOI: 10.5194/isprs-annals-iii-3-339-2016
• 发表时间: 2016-06
• 期刊: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
• 作者: A. Paul;F. Rottensteiner;C. Heipke