A2-FPN for Semantic Segmentation of Fine-Resolution Remotely Sensed Images

TL;DR

This paper introduces A2-FPN, a novel neural network framework that enhances semantic segmentation of fine-resolution remotely sensed images by integrating an attention-guided feature aggregation module into the feature pyramid network architecture.

Contribution

The paper proposes the A2-FPN framework, which improves feature aggregation in FPN using an attention module, leading to better segmentation accuracy on remote sensing images.

Findings

A2-FPN outperforms baseline models on three datasets.

Attention Aggregation Module enhances multi-scale feature learning.

The approach achieves state-of-the-art segmentation accuracy.

Abstract

Semantic segmentation using fine-resolution remotely sensed images plays a critical role in many practical applications, such as urban planning, environmental protection, natural and anthropogenic landscape monitoring, etc. However, the automation of semantic segmentation, i.e., automatic categorization/labeling and segmentation is still a challenging task, particularly for fine-resolution images with huge spatial and spectral complexity. Addressing such a problem represents an exciting research field, which paves the way for scene-level landscape pattern analysis and decision making. In this paper, we propose an approach for automatic land segmentation based on the Feature Pyramid Network (FPN). As a classic architecture, FPN can build a feature pyramid with high-level semantics throughout. However, intrinsic defects in feature extraction and fusion hinder FPN from further aggregating more discriminative features. Hence, we propose an Attention Aggregation Module (AAM) to enhance multi-scale feature learning through attention-guided feature aggregation. Based on FPN and AAM, a novel framework named Attention Aggregation Feature Pyramid Network (A2-FPN) is developed for semantic segmentation of fine-resolution remotely sensed images. Extensive experiments conducted on three datasets demonstrate the effectiveness of our A2 -FPN in segmentation accuracy. Code is available at https://github.com/lironui/A2-FPN.