Inductive transfer-learning for the classification of aerial and satellite images using Bayesian methods

使用贝叶斯方法对航空和卫星图像进行归纳迁移学习

• 批准号: 246374192
• 负责人: Professor Dr.-Ing. Jörn Ostermann
• 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 2015-12-31
• 项目状态: 已结题
• 来源: https://gepris.dfg.de/gepris/projekt/246374192?language=en
• 关键词: Inductive; transfer; learning; classification; aerial

High-resolution aerial- and satellite imagery are the most important sources of spatial information in remote sensing. Classification of these images using supervised learning algorithms is an essential procedure for image processing and interpretation. This requires a training-sample which must be carefully prepared in a laborious process. One paradigm that may help in reducing manual work during this process is called transfer-learning. A robust transfer-model allows us to reuse training-samples from similar data-sets that are related to our target image in either space (in close vicinity) or time (multi-temporal images). The critical issue is to automatically determine when this transfer will actually improve classification results.The aim of this project is the development and evaluation of such a transfer-model. The parameters of this model will be estimated from all available training-samples using a Bayesian estimator, which also requires a carefully devised prior-probability. Bayesian methods have already proved themselves on a wide range of tasks. Mainly, because they allow robust estimation even when only a minimal amount of data is available and secondly, because they allow methodical modelling of uncertainty and unknown parameters. The estimator will be implemented using modern simulation-based methods, such as Marko-Chain-Monte-Carlo (MCMC).Among the increased robustness compared to existing methods, the main innovations of this project can be summarized as follows: (1) Assessing the usefulness for knowledge transfer of a training-sample is a critical issue. Existing methods are often too optimistic (thus causing negative transfer) or require a large training sample from the target image. Our transfer-model will extend current notions of transferability by a new criteria. This will make our model more robust and more conservative when the available data allows no conclusive decision. (2) Our system combines the instance-transfer-strategy and the feature-representation-transfer-strategy in a unified transfer-model. (3) Existing transfer-methods are usually deeply integrated into a specific classification-method. On the other hand our transfer-model can be utilized with basically any classification-method through a thin abstract interface.A research project of Professor Heipke (Institut für Photogrammetrie und GeoInformation, Leibniz Universität Hannover) will cover a different aspect on the topic of transfer-learning. As part of a research cooperation we plan to share data and results.

高分辨率航空和卫星图像是遥感中最重要的空间信息来源。使用监督学习算法对这些图像进行分类是图像处理和解释的基本步骤。这需要一个训练样本，这个样本必须经过艰苦的过程仔细准备。在这一过程中，一种可能有助于减少体力劳动的范例被称为迁移学习。一个稳健的转移模型允许我们重复使用来自相似数据集的训练样本，这些样本与我们的目标图像在空间上(在近距离内)或时间上(多时间图像)相关。关键的问题是自动确定这种转移何时会真正改善分类结果。本项目的目的是开发和评估这样的转移模型。该模型的参数将使用贝叶斯估计器从所有可用的训练样本中估计出来，这也需要精心设计的先验概率。贝叶斯方法已经在广泛的任务中证明了自己。主要是因为它们允许稳健估计，即使只有最少量的数据可用；其次，因为它们允许对不确定性和未知参数进行有条不紊的建模。该估值器将使用基于仿真的现代方法，如马尔科链-蒙特卡罗方法(MCMC)来实现。与现有方法相比，本项目的主要创新之处在于：(1)评估训练样本对知识转移的有用性是一个关键问题。现有的方法往往过于乐观(从而导致负迁移)，或者需要来自目标图像的大的训练样本。我们的转让模型将以新的标准扩展当前的可转让概念。这将使我们的模型在现有数据不允许做出决定性决定的情况下更加稳健和保守。(2)将实例迁移策略和特征表示迁移策略结合在一个统一的迁移模型中。(3)现有的转移方法通常被深度整合到一种特定的分类方法中。另一方面，我们的迁移模型可以通过一个薄的抽象界面使用基本上任何分类方法。Heipke教授(汉诺威莱布尼茨大学摄影语法和地理信息研究所)的一个研究项目将涵盖迁移学习主题的另一个方面。作为研究合作的一部分，我们计划共享数据和结果。

项目成果

Soft Margin Bayes-Point-Machine Classification via Adaptive Direction Sampling

通过自适应方向采样进行软边距贝叶斯点机器分类

• DOI: 10.1007/978-3-319-59126-1_26
• 发表时间: 2017
• 作者: Karsten Vogt;Jörn Ostermann
• 通讯作者: Jörn Ostermann

Unsupervised Source Selection for Domain Adaptation

用于域适应的无监督源选择

• DOI: 10.14358/pers.84.5.249
• 发表时间: 2018
• 期刊: Photogrammetric Engineering and Remote Sensing
• 影响因子: 1.3
• 作者: Karsten Vogt;Andreas Paul;Franz Rottensteiner;Jörn Ostermann;Christian Heipke
• 通讯作者: Christian Heipke

BOOSTED UNSUPERVISED MULTI-SOURCE SELECTION FOR DOMAIN ADAPTATION

• DOI: 10.5194/isprs-annals-iv-1-w1-229-2017
• 发表时间: 2017-05
• 期刊: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
• 作者: Karsten Vogt;A. Paul;J. Ostermann;F. Rottensteiner;C. Heipke