Fast Portrait Segmentation with Highly Light-weight Network
This work addresses efficient portrait segmentation for applications requiring real-time processing, but it is incremental as it builds on existing light-weight network designs.
The paper tackles fast portrait segmentation by introducing a highly light-weight backbone (HLB) with a bottleneck-based factorized block (BFB), resulting in fewer parameters and faster runtime while maintaining competitive accuracy with state-of-the-art methods.
In this paper, we describe a fast and light-weight portrait segmentation method based on a new highly light-weight backbone (HLB) architecture. The core element of HLB is a bottleneck-based factorized block (BFB) that has much fewer parameters than existing alternatives while keeping good learning capacity. Consequently, the HLB-based portrait segmentation method can run faster than the existing methods yet retaining the competitive accuracy performance with state-of-the-arts. Experiments conducted on two benchmark datasets demonstrate the effectiveness and efficiency of our method.