arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.11274cs.CV
收藏

一种新的多注意力驱动的多标记遥感图像分类系统

A Novel Multi-Attention Driven System For Multi-Label Remote Sensing Image Classification

Gencer Sumbul, Begüm Demir

摘要:

本文提出了一种新的多注意力驱动的系统,联合利用卷积神经网络(CNN)和递归神经网络(RNN)的背景下,多标签遥感(RS)图像分类。拟议的系统包括四个主要模块。第一个模块的目的是提取初步的本地描述符的遥感图像波段,可以与不同的空间分辨率。为此,我们引入了K分支CNN,其中每个分支提取具有相同空间分辨率的图像带的描述符。第二个模块的目的是建立本地描述符之间的空间关系模型。这是通过双向RNN架构实现的,其中长短期记忆节点通过考虑局部区域(图像块)的空间关系来丰富局部描述符。第三个模块旨在为本地描述符定义多个注意力分数。这是通过一种新的基于块的多注意力机制,考虑到联合出现的多个土地覆盖类,并提供了基于注意力的本地描述符。最后一个模块利用这些描述符进行多标签RS图像分类。BigEarthNet是一个大规模的哨兵-2基准存档上获得的实验结果表明,所提出的方法相比,最先进的方法的有效性。

英文摘要:

This paper presents a novel multi-attention driven system that jointly exploits Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) in the context of multi-label remote sensing (RS) image classification. The proposed system consists of four main modules. The first module aims to extract preliminary local descriptors of RS image bands that can be associated to different spatial resolutions. To this end, we introduce a K-Branch CNN, in which each branch extracts descriptors of image bands that have the same spatial resolution. The second module aims to model spatial relationship among local descriptors. This is achieved by a bidirectional RNN architecture, in which Long Short-Term Memory nodes enrich local descriptors by considering spatial relationships of local areas (image patches). The third module aims to define multiple attention scores for local descriptors. This is achieved by a novel patch-based multi-attention mechanism that takes into account the joint occurrence of multiple land-cover classes and provides the attention-based local descriptors. The last module exploits these descriptors for multi-label RS image classification. Experimental results obtained on the BigEarthNet that is a large-scale Sentinel-2 benchmark archive show the effectiveness of the proposed method compared to a state of the art method.

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。

↑