Boundary-Aware Network for Fast and High-Accuracy Portrait Segmentation
arXiv:1901.03814
Abstract
Compared with other semantic segmentation tasks, portrait segmentation requires both higher precision and faster inference speed. However, this problem has not been well studied in previous works. In this paper, we propose a lightweight network architecture, called Boundary-Aware Network (BANet) which selectively extracts detail information in boundary area to make high-quality segmentation output with real-time( >25FPS) speed. In addition, we design a new loss function called refine loss which supervises the network with image level gradient information. Our model is able to produce finer segmentation results which has richer details than annotations.
References in corpus (9)
- ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- ICNet for Real-Time Semantic Segmentation on High-Resolution Images
- Learning a Discriminative Feature Network for Semantic Segmentation
- ExFuse: Enhancing Feature Fusion for Semantic Segmentation
- COCO-Stuff: Thing and Stuff Classes in Context
- Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation
- Fast Deep Matting for Portrait Animation on Mobile Phone
- Boundary-sensitive Network for Portrait Segmentation