UV-Mamba: A DCN-Enhanced State Space Model for Urban Village Boundary Identification in High-Resolution Remote Sensing Images

TL;DR

UV-Mamba is a neural network model that accurately identifies urban village boundaries in high-resolution remote sensing images, overcoming memory issues with deformable convolutions and achieving state-of-the-art results.

Contribution

The paper introduces UV-Mamba, a novel neural network architecture that enhances boundary detection in remote sensing images using deformable state space models.

Findings

Achieves 73.3% and 78.1% IoU on Beijing and Xi'an datasets.

Outperforms previous models by 1.2% and 3.4% IoU.

6x faster inference and 40x smaller model size.

Abstract

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.