arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2004.13390cs.LGstat.ML
收藏

基于元学习的Few-Shot土地覆盖分类

Meta-Learning for Few-Shot Land Cover Classification

Technical University of Munich(慕尼黑工业大学);Stanford University(斯坦福大学)

Marc Rußwurm, Sherrie Wang, Marco Körner, David Lobell

摘要:

地球表面的表现形式因地理区域而异。例如,城市地区的外观在各大洲之间不同,季节性影响植被的外观。为了捕捉单一类别(如城市或植被)中的多样性,需要大的模型容量,因此需要大的数据集。在这项工作中,我们提出了一个不同的视角,并将这种多样性视为一个归纳迁移学习问题,其中来自一个区域的很少数据样本允许模型适应一个看不见的区域。我们评估模型无关的元学习(MAML)算法的分类和分割任务,使用全球和区域分布的数据集。我们发现,当源域和目标域不同时,Few-Shot模型自适应优于具有常规梯度下降和微调的预训练(1)Sen12MS数据集和(2)DeepGlobe数据。这表明,使用元学习的模型优化可能有利于地球科学中的任务,这些任务的数据显示出区域之间的高度多样性,而传统的基于梯度的监督学习在没有特征或标签偏移的情况下仍然适用。

英文摘要:

The representations of the Earth's surface vary from one geographic region to another. For instance, the appearance of urban areas differs between continents, and seasonality influences the appearance of vegetation. To capture the diversity within a single category, like as urban or vegetation, requires a large model capacity and, consequently, large datasets. In this work, we propose a different perspective and view this diversity as an inductive transfer learning problem where few data samples from one region allow a model to adapt to an unseen region. We evaluate the model-agnostic meta-learning (MAML) algorithm on classification and segmentation tasks using globally and regionally distributed datasets. We find that few-shot model adaptation outperforms pre-training with regular gradient descent and fine-tuning on (1) the Sen12MS dataset and (2) DeepGlobe data when the source domain and target domain differ. This indicates that model optimization with meta-learning may benefit tasks in the Earth sciences whose data show a high degree of diversity from region to region, while traditional gradient-based supervised learning remains suitable in the absence of a feature or label shift.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑