论文标题
跨域的功能转换几乎没有遥控遥感场景分类
Feature Transformation for Cross-domain Few-shot Remote Sensing Scene Classification
论文作者
论文摘要
由于远程成像和遥感图像之间较大差异的空间分辨率增加，因此有效地对遥感场景进行分类仍然是一个挑战。现有的研究大大改善了遥感场景分类（RSSC）的性能。但是，这些方法不适用于跨域几乎没有射击问题，而目标域则使用非常有限的训练样本，并且与源域具有不同的数据分布。为了提高模型的适用性，我们在本文中提出了特征转换模块（FTM）。 FTM通过具有可忽略不计的附加参数的非常简单的仿射操作将在源域上学习的特征分布转移到目标域的特征分布。此外，如果可用的培训数据很少，可以有效地了解目标领域的FTM，并且对特定的网络结构不可知。 RSSC和土地覆盖映射任务的实验验证了其处理跨域几乎没有问题的能力。通过与直接填充进行比较，FTM可以实现更好的性能，并具有更好的可传递性和细粒度的可区分性。 \ textit {代码将公开可用。}
Effectively classifying remote sensing scenes is still a challenge due to the increasing spatial resolution of remote imaging and large variances between remote sensing images. Existing research has greatly improved the performance of remote sensing scene classification (RSSC). However, these methods are not applicable to cross-domain few-shot problems where target domain is with very limited training samples available and has a different data distribution from source domain. To improve the model's applicability, we propose the feature-wise transformation module (FTM) in this paper. FTM transfers the feature distribution learned on source domain to that of target domain by a very simple affine operation with negligible additional parameters. Moreover, FTM can be effectively learned on target domain in the case of few training data available and is agnostic to specific network structures. Experiments on RSSC and land-cover mapping tasks verified its capability to handle cross-domain few-shot problems. By comparison with directly finetuning, FTM achieves better performance and possesses better transferability and fine-grained discriminability. \textit{Code will be publicly available.}
