Semantic Attention and Scale Complementary Network for Instance Segmentation in Remote Sensing Images
journal contributionposted on 05.08.2021, 13:23 by T Zhang, X Zhang, P Zhu, X Tang, C Li, LC Jiao, Huiyu Zhou
In this paper, we focus on the challenging multi-category instance segmentation problem in remote sensing images(RSIs), which aims at predicting the categories of all instances and localizing them with pixel-level masks. Although many land-mark frameworks have demonstrated promising performance in instance segmentation, the complexity in the background and scale variability instances still remain challenging for in-stance segmentation of RSIs. To address the above problems, we propose an end-to-end multi-category instance segmentation model, namely Semantic Attention and Scale Complementary Network, which mainly consists of a Semantic Attention (SEA)module and a Scale Complementary Mask Branch (SCMB).The SEA module contains a simple fully convolutional semantic segmentation branch with extra supervision to strengthen the activation of interest instances on the feature map and reduce the background noise’s interference. To handle the under-segmentation of geospatial instances with large varying scales, we design the SCMB that extends the original single-scale mask branch to trident mask branches and introduces complementary mask supervision at different scales to sufficiently leverage the multi-scale information. We conduct comprehensive experiments to evaluate the effectiveness of our proposed method on the iSAID dataset and the NWPU Instance Segmentation dataset and achieve promising performance.