A Bag of Tricks for Fine-Grained Roof Extraction

Abstract

In this article, we introduce the method we used in the 2023 IEEE GRSS Data Fusion Contest Track 1. The task demands a fine-grained classification method for semantic urban reconstruction. Our experiments are based on Swin transformer, combined with Double-Head module and RFLA (Gaussian Receptive Field based Lable Assignment) strategy, which can effectively improve model's performance on small objects. Experimental results show that our method can bring significant improvement. We achieved the 4 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">th</sup> place in the final leader board.