Road Segmentation for Remote Sensing Images using Adversarial Spatial Pyramid Networks

Abstract

Road extraction in remote sensing images is of great importance for a wide range of applications. Because of the complex background, and high density, most of the existing methods fail to accurately extract a road network that appears correct and complete. Moreover, they suffer from either insufficient training data or high costs of manual annotation. To address these problems, we introduce a new model to apply structured domain adaption for synthetic image generation and road segmentation. We incorporate a feature pyramid network into generative adversarial networks to minimize the difference between the source and target domains. A generator is learned to produce quality synthetic images, and the discriminator attempts to distinguish them. We also propose a feature pyramid network that improves the performance of the proposed model by extracting effective features from all the layers of the network for describing different scales objects. Indeed, a novel scale-wise architecture is introduced to learn from the multi-level feature maps and improve the semantics of the features. For optimization, the model is trained by a joint reconstruction loss function, which minimizes the difference between the fake images and the real ones. A wide range of experiments on three datasets prove the superior performance of the proposed approach in terms of accuracy and efficiency. In particular, our model achieves state-of-the-art 78.86 IOU on the Massachusetts dataset with 14.89M parameters and 86.78B FLOPs, with 4x fewer FLOPs but higher accuracy (+3.47% IOU) than the top performer among state-of-the-art approaches used in the evaluation.

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Squeeze-and-Excitation Networks
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Generating Multi-label Discrete Patient Records using Generative Adversarial Networks
• Nested Network with Two-Stream Pyramid for Salient Object Detection in Optical Remote Sensing Images
• Weakly Supervised Adversarial Domain Adaptation for Semantic Segmentation in Urban Scenes
• Road Segmentation in SAR Satellite Images with Deep Fully-Convolutional Neural Networks
• Improving GANs Using Optimal Transport
• Residual Pyramid Learning for Single-Shot Semantic Segmentation
• Learning Spatial Pyramid Attentive Pooling in Image Synthesis and Image-to-Image Translation

Cited by in corpus (6)

• UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery
• Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training for Road Segmentation of Remote Sensing Images
• MACU-Net for Semantic Segmentation of Fine-Resolution Remotely Sensed Images
• MultiScale Probability Map guided Index Pooling with Attention-based learning for Road and Building Segmentation
• Rotation Equivariant Feature Image Pyramid Network for Object Detection in Optical Remote Sensing Imagery
• Multi-patch Feature Pyramid Network for Weakly Supervised Object Detection in Optical Remote Sensing Images