BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
This addresses the problem of poor performance in real-time semantic segmentation for applications like autonomous driving, though it is an incremental improvement over existing methods.
The paper tackles the trade-off between spatial resolution and inference speed in real-time semantic segmentation by proposing the Bilateral Segmentation Network (BiSeNet), which achieves 68.4% Mean IOU on Cityscapes at 105 FPS.
Semantic segmentation requires both rich spatial information and sizeable receptive field. However, modern approaches usually compromise spatial resolution to achieve real-time inference speed, which leads to poor performance. In this paper, we address this dilemma with a novel Bilateral Segmentation Network (BiSeNet). We first design a Spatial Path with a small stride to preserve the spatial information and generate high-resolution features. Meanwhile, a Context Path with a fast downsampling strategy is employed to obtain sufficient receptive field. On top of the two paths, we introduce a new Feature Fusion Module to combine features efficiently. The proposed architecture makes a right balance between the speed and segmentation performance on Cityscapes, CamVid, and COCO-Stuff datasets. Specifically, for a 2048x1024 input, we achieve 68.4% Mean IOU on the Cityscapes test dataset with speed of 105 FPS on one NVIDIA Titan XP card, which is significantly faster than the existing methods with comparable performance.