Satellite Image Semantic Segmentation

12 Oct 2021 · Eric Guérin, Killian Oechslin, Christian Wolf, Benoît Martinez ·

In this paper, we propose a method for the automatic semantic segmentation of satellite images into six classes (sparse forest, dense forest, moor, herbaceous formation, building, and road). We rely on Swin Transformer architecture and build the dataset from IGN open data. We report quantitative and qualitative segmentation results on this dataset and discuss strengths and limitations. The dataset and the trained model are made publicly available.

Code

Add Remove Mark official

koechslin/swin-transformer-semantic… official

34

Tasks

Add Remove

2D Semantic Segmentation

Semantic Segmentation

Datasets

Add Datasets introduced or used in this paper

Results from the Paper

Add Remove

Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods

Add Remove

Absolute Position Encodings • Adam • BPE • Dense Connections • Dropout • Label Smoothing • Layer Normalization • Linear Layer • Multi-Head Attention • Position-Wise Feed-Forward Layer • Residual Connection • Scaled Dot-Product Attention • Softmax • Stochastic Depth • Swin Transformer • Transformer