Multi-Task Learning for Semantic Change Detection on VHR Remote Sensing Images | |
Yuan Zhou; Jiahang Zhu; Leigang Huo; Chunlei Huo | |
2022-07 | |
会议日期 | 2022-7-17 |
会议地点 | Kuala Lumpur, Malaysia |
关键词 | Change detection Multi-task learning Semantic segmentation |
DOI | 10.1109/IGARSS46834.2022.9883651 |
英文摘要 | Remote Sensing Images Change Detection (RSICD) aims to locate the changed regions between bitemporal very-high-resolution (VHR) sensing images. However, existing deep learning-based RSICD methods are from the requirements by practical application, mainly due to the low feature discrimination and limited accuracy. We propose a novel multi-task and multi-temporal encoder-decoder changed detection network (MMNet) for VHR images, which accomplished both semantic segmentation and change detection at the same time. The encoder extracts multi-level contextual information, which contains two semantic segmentation branches (SSB) and a change detection branch (CDB). In this way, change representation constrains semantic representation during training, which introduces a novel loss function to ensure the semantic consistency within the unchanged regions. Furthermore, to utilize multi-level feature representation for enhancing the separability of features, a multi-scale feature fusion module (MFFM) is presented. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/52028] |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Chunlei Huo |
作者单位 | 1.Nanning Normal University 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Yuan Zhou,Jiahang Zhu,Leigang Huo,et al. Multi-Task Learning for Semantic Change Detection on VHR Remote Sensing Images[C]. 见:. Kuala Lumpur, Malaysia. 2022-7-17. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论