PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation

Abstract

Aerial Image Segmentation is a particular semantic segmentation problem and has several challenging characteristics that general semantic segmentation does not have. There are two critical issues: The one is an extremely foreground-background imbalanced distribution, and the other is multiple small objects along with the complex background. Such problems make the recent dense affinity context modeling perform poorly even compared with baselines due to over-introduced background context. To handle these problems, we propose a point-wise affinity propagation module based on the Feature Pyramid Network (FPN) framework, named PointFlow. Rather than dense affinity learning, a sparse affinity map is generated upon selected points between the adjacent features, which reduces the noise introduced by the background while keeping efficiency. In particular, we design a dual point matcher to select points from the salient area and object boundaries, respectively. Experimental results on three different aerial segmentation datasets suggest that the proposed method is more effective and efficient than state-of-the-art general semantic segmentation methods. Especially, our methods achieve the best speed and accuracy trade-off on three aerial benchmarks. Further experiments on three general semantic segmentation datasets prove the generality of our method. Code will be provided in (https: //github.com/lxtGH/PFSegNets).

accepted by CVPR2021

References in corpus (16)

• Rethinking Atrous Convolution for Semantic Image Segmentation
• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• OCNet: Object Context Network for Scene Parsing
• Deep High-Resolution Representation Learning for Visual Recognition
• Land cover mapping at very high resolution with rotation equivariant CNNs: towards small yet accurate models
• Semantic Understanding of Scenes through the ADE20K Dataset
• Context Encoding for Semantic Segmentation
• Dual Graph Convolutional Network for Semantic Segmentation
• Expectation-Maximization Attention Networks for Semantic Segmentation
• Global Aggregation then Local Distribution in Fully Convolutional Networks
• ACFNet: Attentional Class Feature Network for Semantic Segmentation
• Involution: Inverting the Inherence of Convolution for Visual Recognition
• Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis
• Semantic Flow for Fast and Accurate Scene Parsing
• Feature Pyramid Transformer