Efficient Remote Sensing Segmentation With Generative Adversarial Transformer

TL;DR

This paper introduces GATrans, an efficient generative adversarial transformer model for high-precision semantic segmentation on embedded devices, combining global transformers and structural similarity losses for improved performance.

Contribution

The paper presents GATrans, a lightweight transformer-based segmentation framework that maintains high accuracy while significantly reducing model size and computational complexity.

Findings

Achieved 90.17% F1 score on Vaihingen dataset

Attained 91.92% overall accuracy

Demonstrated efficiency suitable for embedded devices

Abstract

Most deep learning methods that achieve high segmentation accuracy require deep network architectures that are too heavy and complex to run on embedded devices with limited storage and memory space. To address this issue, this paper proposes an efficient Generative Adversarial Transfomer (GATrans) for achieving high-precision semantic segmentation while maintaining an extremely efficient size. The framework utilizes a Global Transformer Network (GTNet) as the generator, efficiently extracting multi-level features through residual connections. GTNet employs global transformer blocks with progressively linear computational complexity to reassign global features based on a learnable similarity function. To focus on object-level and pixel-level information, the GATrans optimizes the objective function by combining structural similarity losses. We validate the effectiveness of our approach through extensive experiments on the Vaihingen dataset, achieving an average F1 score of 90.17% and an overall accuracy of 91.92%.