用可变形卷积改进状态空间模型，精准识别高分遥感图像中的城中村边界
UV-Mamba: A DCN-Enhanced State Space Model for Urban Village Boundary Identification in High-Resolution Remote Sensing Images
- 引入可变形卷积增强状态空间模型，缓解大图像下长序列建模的遗忘问题
- 在北京和西安数据集上分别达到73.3%和78.1%的交并比，优于此前最佳模型
- 参数量减少40倍、推理速度提升6倍，适合实际部署于大规模遥感分析
由于地理环境多样、景观复杂且聚居密度高，利用遥感图像自动识别城中村边界仍是极具挑战的任务。本文提出一种新型高效神经网络模型UV-Mamba，用于高分辨率遥感图像中的精确边界检测。该模型通过引入可变形卷积（DCN），缓解了状态空间模型（SSM）在图像尺寸增大时出现的长序列建模记忆丢失问题。其架构采用编码器-解码器结构，编码器包含四个可变形状态空间增强模块，实现高效多层级语义提取；解码器则用于融合提取的语义信息。在两个大规模数据集上的实验表明，UV-Mamba达到当前最优性能：在北京和西安数据集上分别取得73.3%和78.1%的交并比（IoU），较前人最佳模型分别提升1.2%和3.4%；同时推理速度提升6倍，参数量减少40倍。源代码与预训练模型已公开于https://github.com/Devin-Egber/UV-Mamba。
原文摘要 · Abstract (English)
Due to the diverse geographical environments, intricate landscapes, and high-density settlements, the automatic identification of urban village boundaries using remote sensing images remains a highly challenging task. This paper proposes a novel and efficient neural network model called UV-Mamba for accurate boundary detection in high-resolution remote sensing images. UV-Mamba mitigates the memory loss problem in lengthy sequence modeling, which arises in state space models with increasing image size, by incorporating deformable convolutions. Its architecture utilizes an encoder-decoder framework and includes an encoder with four deformable state space augmentation blocks for efficient multi-level semantic extraction and a decoder to integrate the extracted semantic information. We conducted experiments on two large datasets showing that UV-Mamba achieves state-of-the-art performance. Specifically, our model achieves 73.3% and 78.1% IoU on the Beijing and Xi'an datasets, respectively, representing improvements of 1.2% and 3.4% IoU over the previous best model while also being 6x faster in inference speed and 40x smaller in parameter count. Source code and pre-trained models are available at https://github.com/Devin-Egber/UV-Mamba.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。