Boundary Corrected Multi-scale Fusion Network for Real-time Semantic Segmentation
This addresses the problem of real-time semantic segmentation for applications like autonomous driving, though it is incremental as it builds on existing lightweight architectures.
The paper tackles the challenge of achieving both high accuracy and real-time speed in semantic segmentation by proposing a Boundary Corrected Multi-scale Fusion Network, which uses a Low-resolution Multi-scale Fusion Module and Boundary Corrected Loss to reduce boundary errors, achieving state-of-the-art balance with 75.3% mIoU on Cityscapes at 45 FPS.
Image semantic segmentation aims at the pixel-level classification of images, which has requirements for both accuracy and speed in practical application. Existing semantic segmentation methods mainly rely on the high-resolution input to achieve high accuracy and do not meet the requirements of inference time. Although some methods focus on high-speed scene parsing with lightweight architectures, they can not fully mine semantic features under low computation with relatively low performance. To realize the real-time and high-precision segmentation, we propose a new method named Boundary Corrected Multi-scale Fusion Network, which uses the designed Low-resolution Multi-scale Fusion Module to extract semantic information. Moreover, to deal with boundary errors caused by low-resolution feature map fusion, we further design an additional Boundary Corrected Loss to constrain overly smooth features. Extensive experiments show that our method achieves a state-of-the-art balance of accuracy and speed for the real-time semantic segmentation.