Ada-DQA: Adaptive Diverse Quality-aware Feature Acquisition for Video Quality Assessment

TL;DR

Ada-DQA introduces an adaptive feature acquisition framework that leverages diverse pretrained models to improve video quality assessment accuracy while reducing computational costs, without requiring additional labeled data.

Contribution

The paper proposes a novel adaptive feature acquisition method using diverse pretrained models and a quality-aware module for improved VQA performance.

Findings

Outperforms state-of-the-art methods on three VQA benchmarks

Reduces inference computational cost significantly

Effectively utilizes diverse pretrained models for quality representation

Abstract

Video quality assessment (VQA) has attracted growing attention in recent years. While the great expense of annotating large-scale VQA datasets has become the main obstacle for current deep-learning methods. To surmount the constraint of insufficient training data, in this paper, we first consider the complete range of video distribution diversity (\ie content, distortion, motion) and employ diverse pretrained models (\eg architecture, pretext task, pre-training dataset) to benefit quality representation. An Adaptive Diverse Quality-aware feature Acquisition (Ada-DQA) framework is proposed to capture desired quality-related features generated by these frozen pretrained models. By leveraging the Quality-aware Acquisition Module (QAM), the framework is able to extract more essential and relevant features to represent quality. Finally, the learned quality representation is utilized as supplementary supervisory information, along with the supervision of the labeled quality score, to guide the training of a relatively lightweight VQA model in a knowledge distillation manner, which largely reduces the computational cost during inference. Experimental results on three mainstream no-reference VQA benchmarks clearly show the superior performance of Ada-DQA in comparison with current state-of-the-art approaches without using extra training data of VQA.