# Lightweight Alpha Matting Network Using Distillation-Based Channel Pruning

Source: [Lightweight Alpha Matting Network Using Distillation-Based Channel Pruning](<https://www.sota2.com/research/paper/68fa6daa1e209131cea3b4f9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:55.742Z

Authors: Donggeun Yoon, Jinsun Park, Donghyeon Cho

Published: 2022-10-14T12:48:40.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2210.07760>)

[PDF](<https://arxiv.org/pdf/2210.07760.pdf>)