Revisiting Video Quality Assessment from the Perspective of Generalization
- URL: http://arxiv.org/abs/2409.14847v1
- Date: Mon, 23 Sep 2024 09:24:55 GMT
- Title: Revisiting Video Quality Assessment from the Perspective of Generalization
- Authors: Xinli Yue, Jianhui Sun, Liangchao Yao, Fan Xia, Yuetang Deng, Tianyi Wang, Lei Li, Fengyun Rao, Jing Lv, Qian Wang, Lingchen Zhao,
- Abstract summary: Short video platforms such as YouTube Shorts, TikTok, and Kwai have led to a surge in User-Generated Content (UGC)
These challenges not only affect performance on test sets but also impact the ability to generalize across different datasets.
We show that adversarial weight perturbations can effectively smooth this landscape, significantly improving the generalization performance.
- Score: 17.695835285573807
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The increasing popularity of short video platforms such as YouTube Shorts, TikTok, and Kwai has led to a surge in User-Generated Content (UGC), which presents significant challenges for the generalization performance of Video Quality Assessment (VQA) tasks. These challenges not only affect performance on test sets but also impact the ability to generalize across different datasets. While prior research has primarily focused on enhancing feature extractors, sampling methods, and network branches, it has largely overlooked the generalization capabilities of VQA tasks. In this work, we reevaluate the VQA task from a generalization standpoint. We begin by analyzing the weight loss landscape of VQA models, identifying a strong correlation between this landscape and the generalization gaps. We then investigate various techniques to regularize the weight loss landscape. Our results reveal that adversarial weight perturbations can effectively smooth this landscape, significantly improving the generalization performance, with cross-dataset generalization and fine-tuning performance enhanced by up to 1.8% and 3%, respectively. Through extensive experiments across various VQA methods and datasets, we validate the effectiveness of our approach. Furthermore, by leveraging our insights, we achieve state-of-the-art performance in Image Quality Assessment (IQA) tasks. Our code is available at https://github.com/XinliYue/VQA-Generalization.
Related papers
- CLIPVQA:Video Quality Assessment via CLIP [56.94085651315878]
We propose an efficient CLIP-based Transformer method for the VQA problem ( CLIPVQA)
The proposed CLIPVQA achieves new state-of-the-art VQA performance and up to 37% better generalizability than existing benchmark VQA methods.
arXiv Detail & Related papers (2024-07-06T02:32:28Z) - GAIA: Rethinking Action Quality Assessment for AI-Generated Videos [56.047773400426486]
Action quality assessment (AQA) algorithms predominantly focus on actions from real specific scenarios and are pre-trained with normative action features.
We construct GAIA, a Generic AI-generated Action dataset, by conducting a large-scale subjective evaluation from a novel causal reasoning-based perspective.
Results show that traditional AQA methods, action-related metrics in recent T2V benchmarks, and mainstream video quality methods perform poorly with an average SRCC of 0.454, 0.191, and 0.519, respectively.
arXiv Detail & Related papers (2024-06-10T08:18:07Z) - Descriptive Image Quality Assessment in the Wild [25.503311093471076]
VLM-based Image Quality Assessment (IQA) seeks to describe image quality linguistically to align with human expression.
We introduce Depicted image Quality Assessment in the Wild (DepictQA-Wild)
Our method includes a multi-functional IQA task paradigm that encompasses both assessment and comparison tasks, brief and detailed responses, full-reference and non-reference scenarios.
arXiv Detail & Related papers (2024-05-29T07:49:15Z) - Ada-DQA: Adaptive Diverse Quality-aware Feature Acquisition for Video
Quality Assessment [25.5501280406614]
Video quality assessment (VQA) has attracted growing attention in recent years.
The great expense of annotating large-scale VQA datasets has become the main obstacle for current deep-learning methods.
An Adaptive Diverse Quality-aware feature Acquisition (Ada-DQA) framework is proposed to capture desired quality-related features.
arXiv Detail & Related papers (2023-08-01T16:04:42Z) - Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models [71.06007696593704]
Blind quality assessment (BVQA) plays an indispensable role in monitoring and improving the end-users' viewing experience in real-world video-enabled media applications.
As an experimental field, the improvements of BVQA models have been measured primarily on a few human-rated VQA datasets.
We conduct a first-of-its-kind computational analysis of VQA datasets via minimalistic BVQA models.
arXiv Detail & Related papers (2023-07-26T06:38:33Z) - Towards Explainable In-the-Wild Video Quality Assessment: A Database and
a Language-Prompted Approach [52.07084862209754]
We collect over two million opinions on 4,543 in-the-wild videos on 13 dimensions of quality-related factors.
Specifically, we ask the subjects to label among a positive, a negative, and a neutral choice for each dimension.
These explanation-level opinions allow us to measure the relationships between specific quality factors and abstract subjective quality ratings.
arXiv Detail & Related papers (2023-05-22T05:20:23Z) - Towards Robust Text-Prompted Semantic Criterion for In-the-Wild Video
Quality Assessment [54.31355080688127]
We introduce a text-prompted Semantic Affinity Quality Index (SAQI) and its localized version (SAQI-Local) using Contrastive Language-Image Pre-training (CLIP)
BVQI-Local demonstrates unprecedented performance, surpassing existing zero-shot indices by at least 24% on all datasets.
We conduct comprehensive analyses to investigate different quality concerns of distinct indices, demonstrating the effectiveness and rationality of our design.
arXiv Detail & Related papers (2023-04-28T08:06:05Z) - UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated
Content [59.13821614689478]
Blind quality prediction of in-the-wild videos is quite challenging, since the quality degradations of content are unpredictable, complicated, and often commingled.
Here we contribute to advancing the problem by conducting a comprehensive evaluation of leading VQA models.
By employing a feature selection strategy on top of leading VQA model features, we are able to extract 60 of the 763 statistical features used by the leading models.
Our experimental results show that VIDEVAL achieves state-of-theart performance at considerably lower computational cost than other leading models.
arXiv Detail & Related papers (2020-05-29T00:39:20Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.