Lightweight Alpha Matting Network Using Distillation-Based Channel Pruning
This work addresses the need for efficient alpha matting on portable devices, offering an incremental improvement over prior lightweight methods.
The paper tackles the problem of creating a lightweight alpha matting model for mobile applications by proposing a distillation-based channel pruning method, resulting in a model that outperforms existing lightweight methods in quantitative and qualitative experiments.
Recently, alpha matting has received a lot of attention because of its usefulness in mobile applications such as selfies. Therefore, there has been a demand for a lightweight alpha matting model due to the limited computational resources of commercial portable devices. To this end, we suggest a distillation-based channel pruning method for the alpha matting networks. In the pruning step, we remove channels of a student network having fewer impacts on mimicking the knowledge of a teacher network. Then, the pruned lightweight student network is trained by the same distillation loss. A lightweight alpha matting model from the proposed method outperforms existing lightweight methods. To show superiority of our algorithm, we provide various quantitative and qualitative experiments with in-depth analyses. Furthermore, we demonstrate the versatility of the proposed distillation-based channel pruning method by applying it to semantic segmentation.