BiSeNet
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
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 2048×1024 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.
Implementations
Result
Method | Cropped | Resized |
---|---|---|
Pixel Accuracy | 94.1 | 93.2 |
Cropped and Resized means two image processing method to make the input image size fixed, it seems like Cropped input images get better result. I guess it's because cropped masks keep the original ground truth information while resized loss it.
Model: https://github.com/ooooverflow/BiSeNet/blob/master/model/build_BiSeNet.py
