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

2021-02-16 · Rui Li, Shunyi Zheng, Ce Zhang, Chenxi Duan, Libo Wang

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.

📄 PDF Abstract BibTeX arXiv:2102.07997

Code (2)

lironui/A2-FPN 공식 구현 pytorch

lironui/FPN-MHA 공식 구현 pytorch

Tasks

Decision Making Scene Understanding Segmentation Semantic Segmentation

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Multi-Head Attention 설명 없음

MACU-Net for Semantic Segmentation of Fine-Resolution Remotely Sensed Images

2020-07-26 · Rui Li, Chenxi Duan, Shunyi Zheng, Ce Zhang 외

Semantic segmentation of remotely sensed images plays an important role in land resource management, yield estimation, and economic assessment. U-Net, a deep encoder-decoder architecture, has been used frequently for ima…

Decoder Image Segmentation Management Medical Image Segmentation+2

Samba: Semantic Segmentation of Remotely Sensed Images with State Space Model

2024-04-02 · Qinfeng Zhu, Yuanzhi Cai, Yuan Fang, Yihan Yang 외

High-resolution remotely sensed images pose a challenge for commonly used semantic segmentation methods such as Convolutional Neural Network (CNN) and Vision Transformer (ViT). CNN-based methods struggle with handling su…

Decoder Mamba Segmentation Semantic Segmentation

Semantic Segmentation on Remotely Sensed Images Using an Enhanced Global Convolutional Network with Channel Attention and Domain Specific Transfer Learning

2019-01-04 · Teerapong Panboonyuen

In the remote sensing domain, it is crucial to complete semantic segmentation on the raster images, e.g., river, building, forest, etc., on raster images. A deep convolutional encoder–decoder (DCED) network is the state-…

Segmentation Semantic Segmentation Transfer Learning

Rethinking Scanning Strategies with Vision Mamba in Semantic Segmentation of Remote Sensing Imagery: An Experimental Study

2024-05-14 · Qinfeng Zhu, Yuan Fang, Yuanzhi Cai, Cheng Chen 외

Deep learning methods, especially Convolutional Neural Networks (CNN) and Vision Transformer (ViT), are frequently employed to perform semantic segmentation of high-resolution remotely sensed images. However, CNNs are co…

Mamba Segmentation Segmentation Of Remote Sensing Imagery Semantic Segmentation

ΩSFormer: Dual-Modal Ω-like Super-Resolution Transformer Network for Cross-scale and High-accuracy Terraced Field Vectorization Extraction

2024-11-26 · Chang Li, Yu Wang, Ce Zhang, Yongjun Zhang

Terraced field is a significant engineering practice for soil and water conservation (SWC). Terraced field extraction from remotely sensed imagery is the foundation for monitoring and evaluating SWC. This study is the fi…

Segmentation Semantic Segmentation Super-Resolution