Affiliation of Author(s):信息科学技术学院
Journal:2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS
Funded by:其他课题
Abstract:In this paper, we focus on ROI extraction with only scribble annotations for remote sensing images (RSIs). The main challenges exist in predicting precise region boundary and suppressing complex background interference in RSIs. To address these issue, we propose a scribble-supervised residual dense dilated network (RD-DN) trained with a novel label update strategy to produce integral ROIs with accurate boundary. Specifically, the hybrid dilated convolution block is introduced as the basic module of the RD-DN, aiming to help provide much denser results. The RD-DN is first trained with only scribble labels to generate initial results. Then, as training phase goes, the label update strategy updates the labels iteratively by combining the initial results and the scribble annotations with a morphological dilation procedure. Comprehensive experiments on the GeoEye-1 dataset demonstrate the superiority of our proposal compared with state-of-the-art ROIs extraction methods.
Indexed by:Essay collection
Volume:1
Translation or Not:no
Date of Publication:2021-01-07
First Author:majie
