Ada-DQA: Adaptive Diverse Quality-aware Feature Acquisition for Video Quality Assessment
This addresses the data scarcity issue in VQA for researchers and practitioners, but it is incremental as it builds on existing pretrained models and distillation techniques.
The paper tackles the problem of insufficient training data for video quality assessment (VQA) by proposing Ada-DQA, which adaptively extracts quality-aware features from diverse pretrained models and uses knowledge distillation to train a lightweight model, achieving superior performance on three benchmarks without extra VQA data.
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.