Lightweight Human Matting Method Based on Pruning and Knowledge Distillation
In recent years,with the wide application of human matting technology,the requirements for its realtime per-formance and accuracy have also increased gradually.Existing lightweight methods are difficult to guarantee accuracy,while higher-precision methods often use larger network structures that cannot meet realtime requirements.In order to solve this problem,a lightweight human matting method based on pruning and knowledge distillation is proposed.This method first obtains a lightweight student network structure through network pruning,and then uses the student network for knowl-edge distillation.Experiments show that this method can effectively reduce parameter quantity and inference time while en-suring model accuracy,and has fewer parameters and higher accuracy than existing lightweight human matting methods.
万方数据
维普
