ST-MFNet Mini: Knowledge Distillation-Driven Frame Interpolation

Cited 2|Views47

Abstract

Currently, one of the major challenges in deep learning-based video frame interpolation (VFI) is the large model size and high computational complexity associated with many high performance VFI approaches. In this paper, we present a distillation-based two-stage workflow for obtaining compressed VFI models which perform competitively compared to the state of the art, but with significantly reduced model size and complexity. Specifically, an optimization-based network pruning method is applied to a state of the art frame interpolation model, ST-MFNet, which suffers from large model size. The resulting network architecture achieves a 91% reduction in parameter numbers and a 35% increase in speed. The performance of the new network is further enhanced through a teacher-student knowledge distillation training process using a Laplacian distillation loss. The final low complexity model, ST-MFNet Mini, achieves a comparable performance to most existing high-complexity VFI methods, only outperformed by the original ST-MFNet. Our source code is available at https://github.com/crispianm/ST-MFNet-Mini

Translated text

Key words

Video frame interpolation,model compression,knowledge distillation

Bibtex

AI Read Science

AI Summary

AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.

Example

Background

Key content

Introduction

Methods

Results

Related work

Fund

Key content

Pretraining has recently greatly promoted the development of natural language processing (NLP)
We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance

Try using models to generate summary,it takes about 60s

Must-Reading Tree

Example

Generate MRT to find the research sequence of this paper