RankDVQA-mini: Knowledge Distillation-Driven Deep Video Quality Assessment

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Feng, Chen, Danier, Duolikun, Wang, Haoran, Zhang, Fan, Vallade, Benoit, Mackin, Alex, Bull, David
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910976691929088
author Feng, Chen
Danier, Duolikun
Wang, Haoran
Zhang, Fan
Vallade, Benoit
Mackin, Alex
Bull, David
author_facet Feng, Chen
Danier, Duolikun
Wang, Haoran
Zhang, Fan
Vallade, Benoit
Mackin, Alex
Bull, David
contents Deep learning-based video quality assessment (deep VQA) has demonstrated significant potential in surpassing conventional metrics, with promising improvements in terms of correlation with human perception. However, the practical deployment of such deep VQA models is often limited due to their high computational complexity and large memory requirements. To address this issue, we aim to significantly reduce the model size and runtime of one of the state-of-the-art deep VQA methods, RankDVQA, by employing a two-phase workflow that integrates pruning-driven model compression with multi-level knowledge distillation. The resulting lightweight full reference quality metric, RankDVQA-mini, requires less than 10% of the model parameters compared to its full version (14% in terms of FLOPs), while still retaining a quality prediction performance that is superior to most existing deep VQA methods. The source code of the RankDVQA-mini has been released at https://chenfeng-bristol.github.io/RankDVQA-mini/ for public evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2312_08864
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle RankDVQA-mini: Knowledge Distillation-Driven Deep Video Quality Assessment
Feng, Chen
Danier, Duolikun
Wang, Haoran
Zhang, Fan
Vallade, Benoit
Mackin, Alex
Bull, David
Image and Video Processing
Computer Vision and Pattern Recognition
Deep learning-based video quality assessment (deep VQA) has demonstrated significant potential in surpassing conventional metrics, with promising improvements in terms of correlation with human perception. However, the practical deployment of such deep VQA models is often limited due to their high computational complexity and large memory requirements. To address this issue, we aim to significantly reduce the model size and runtime of one of the state-of-the-art deep VQA methods, RankDVQA, by employing a two-phase workflow that integrates pruning-driven model compression with multi-level knowledge distillation. The resulting lightweight full reference quality metric, RankDVQA-mini, requires less than 10% of the model parameters compared to its full version (14% in terms of FLOPs), while still retaining a quality prediction performance that is superior to most existing deep VQA methods. The source code of the RankDVQA-mini has been released at https://chenfeng-bristol.github.io/RankDVQA-mini/ for public evaluation.
title RankDVQA-mini: Knowledge Distillation-Driven Deep Video Quality Assessment
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.08864