Real-time Semantic Segmentation with Fast Attention
This work addresses the problem of real-time semantic segmentation for applications like autonomous driving and video analysis, offering a significant speed improvement without sacrificing accuracy.
The paper tackles the challenge of achieving high accuracy in real-time semantic segmentation by proposing a novel architecture with fast spatial attention, which reduces computational costs while maintaining rich spatial context. It demonstrates state-of-the-art performance, achieving 74.4% mIoU at 72 FPS and 75.5% mIoU at 58 FPS on Cityscapes, about 50% faster than previous methods with similar accuracy.
In deep CNN based models for semantic segmentation, high accuracy relies on rich spatial context (large receptive fields) and fine spatial details (high resolution), both of which incur high computational costs. In this paper, we propose a novel architecture that addresses both challenges and achieves state-of-the-art performance for semantic segmentation of high-resolution images and videos in real-time. The proposed architecture relies on our fast spatial attention, which is a simple yet efficient modification of the popular self-attention mechanism and captures the same rich spatial context at a small fraction of the computational cost, by changing the order of operations. Moreover, to efficiently process high-resolution input, we apply an additional spatial reduction to intermediate feature stages of the network with minimal loss in accuracy thanks to the use of the fast attention module to fuse features. We validate our method with a series of experiments, and show that results on multiple datasets demonstrate superior performance with better accuracy and speed compared to existing approaches for real-time semantic segmentation. On Cityscapes, our network achieves 74.4$\%$ mIoU at 72 FPS and 75.5$\%$ mIoU at 58 FPS on a single Titan X GPU, which is~$\sim$50$\%$ faster than the state-of-the-art while retaining the same accuracy.