Towards Generalized Video Quality Assessment: A Weak-to-Strong Learning Paradigm

• URL: http://arxiv.org/abs/2505.03631v3
• Date: Wed, 15 Oct 2025 05:13:05 GMT
• Title: Towards Generalized Video Quality Assessment: A Weak-to-Strong Learning Paradigm
• Authors: Linhan Cao, Wei Sun, Xiangyang Zhu, Kaiwei Zhang, Jun Jia, Yicong Peng, Dandan Zhu, Guangtao Zhai, Xiongkuo Min,
• Abstract summary: Video quality assessment (VQA) seeks to predict the perceptual quality of a video in alignment with human visual perception.<n>The dominant VQA paradigm relies on supervised training with human-labeled datasets.<n>We explore weak-to-strong (W2S) learning as a new paradigm for advancing VQA without reliance on large-scale human-labeled datasets.
• Score: 76.63001244080313
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Video quality assessment (VQA) seeks to predict the perceptual quality of a video in alignment with human visual perception, serving as a fundamental tool for quantifying quality degradation across video processing workflows. The dominant VQA paradigm relies on supervised training with human-labeled datasets, which, despite substantial progress, still suffers from poor generalization to unseen video content. Moreover, its reliance on human annotations -- which are labor-intensive and costly -- makes it difficult to scale datasets for improving model generalization. In this work, we explore weak-to-strong (W2S) learning as a new paradigm for advancing VQA without reliance on large-scale human-labeled datasets. We first provide empirical evidence that a straightforward W2S strategy allows a strong student model to not only match its weak teacher on in-domain benchmarks but also surpass it on out-of-distribution (OOD) benchmarks, revealing a distinct weak-to-strong effect in VQA. Building on this insight, we propose a novel framework that enhances W2S learning from two aspects: (1) integrating homogeneous and heterogeneous supervision signals from diverse VQA teachers -- including off-the-shelf VQA models and synthetic distortion simulators -- via a learn-to-rank formulation, and (2) iterative W2S training, where each strong student is recycled as the teacher in subsequent cycles, progressively focusing on challenging cases. Extensive experiments show that our method achieves state-of-the-art results across both in-domain and OOD benchmarks, with especially strong gains in OOD scenarios. Our findings highlight W2S learning as a principled route to break annotation barriers and achieve scalable generalization in VQA, with implications extending to broader alignment and evaluation tasks.

Related papers

• Vision Large Language Models Are Good Noise Handlers in Engagement Analysis [54.397912827957164]
  We propose a framework leveraging Vision Large Language Models (VLMs) to refine annotations and guide the training process.<n>Our framework uses a questionnaire to extract behavioral cues and split data into high- and low-reliability subsets.<n>We demonstrate that classical computer vision models trained on refined high-reliability subsets and enhanced with our curriculum strategy show improvements.
  arXiv  Detail & Related papers  (2025-11-18T18:50:26Z)
• Q-CLIP: Unleashing the Power of Vision-Language Models for Video Quality Assessment through Unified Cross-Modal Adaptation [33.51239538610773]
  Vision-Language Models (VLMs) have shown remarkable generalization capabilities across a wide range of visual tasks.<n>We propose Q-CLIP, the first fully VLMs-based framework for Video Quality Assessment (VQA)
  arXiv  Detail & Related papers  (2025-08-08T07:36:01Z)
• VQAThinker: Exploring Generalizable and Explainable Video Quality Assessment via Reinforcement Learning [50.34205095371895]
  Video quality assessment aims to objectively quantify perceptual quality degradation.<n>Existing VQA models suffer from two critical limitations.<n>We propose textbfVQAThinker, a reasoning-based VQA framework.
  arXiv  Detail & Related papers  (2025-08-08T06:16:23Z)
• VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning [21.35520258725298]
  VQ-Insight is a novel reasoning-style framework for AIGC video quality assessment.<n>It combines image quality warm-up, general task-specific temporal learning, and joint optimization with the video generation model.<n>It consistently outperforms state-of-the-art baselines in preference comparison, multi-dimension scoring, and natural video scoring.
  arXiv  Detail & Related papers  (2025-06-23T12:20:14Z)
• Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment [10.701522670464463]
  multimodal large language models (MLLMs) can proficiently evaluate visual quality through interpretable assessments.<n>We propose a unified two-stage training framework comprising a cold-start stage and a reinforcement learning-based fine-tuning stage.<n>We designate the models derived from these two stages as Q-Ponder-CI and Q-Ponder.
  arXiv  Detail & Related papers  (2025-06-03T10:11:51Z)
• Scaling-up Perceptual Video Quality Assessment [54.691252495691955]
  We show how to efficiently build high-quality, human-in-the-loop VQA multi-modal instruction databases.<n>Our focus is on the technical and aesthetic quality dimensions, with abundant in-context instruction data to provide fine-grained VQA knowledge.<n>Our results demonstrate that our models achieve state-of-the-art performance in both quality understanding and rating tasks.
  arXiv  Detail & Related papers  (2025-05-28T16:24:52Z)
• Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1 [53.894789613838654]
  We introduce SEED-Bench-R1, a benchmark designed to evaluate post-training methods for MLLMs in video understanding.<n>It includes intricate real-world videos and complex everyday planning tasks in the format of multiple-choice questions.<n>Using Qwen2-VL-Instruct-7B as a base model, we compare RL with supervised fine-tuning (SFT)<n>Our detailed analysis reveals that RL enhances visual perception but often produces less coherent reasoning chains.
  arXiv  Detail & Related papers  (2025-03-31T17:55:23Z)
• Video Quality Assessment: A Comprehensive Survey [55.734935003021576]
  Video quality assessment (VQA) is an important processing task, aiming at predicting the quality of videos in a manner consistent with human judgments of perceived quality.<n>We present a survey of recent progress in the development of VQA algorithms and the benchmarking studies and databases that make them possible.
  arXiv  Detail & Related papers  (2024-12-04T05:25:17Z)
• VideoEval: Comprehensive Benchmark Suite for Low-Cost Evaluation of Video Foundation Model [22.188795668927586]
  Video Foundation Models (VFMs) have made significant progress recently. Existing benchmarks and evaluation protocols are often limited by relatively poor diversity, high evaluation costs, and saturated performance metrics. We build a comprehensive benchmark suite to address these issues, namely VideoEval.
  arXiv  Detail & Related papers  (2024-07-09T01:49:08Z)
• 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)
• PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wild [27.195339506769457]
  Video quality assessment (VQA) is a challenging problem due to the numerous factors that can affect the perceptual quality of a video. Annotating the Mean opinion score (MOS) for videos is expensive and time-consuming, which limits the scale of VQA datasets. We propose a VQA method named PTM-VQA, which leverages PreTrained Models to transfer knowledge from models pretrained on various pre-tasks.
  arXiv  Detail & Related papers  (2024-05-28T02:37:29Z)
• 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)
• CONVIQT: Contrastive Video Quality Estimator [63.749184706461826]
  Perceptual video quality assessment (VQA) is an integral component of many streaming and video sharing platforms. Here we consider the problem of learning perceptually relevant video quality representations in a self-supervised manner. Our results indicate that compelling representations with perceptual bearing can be obtained using self-supervised learning.
  arXiv  Detail & Related papers  (2022-06-29T15:22:01Z)
• Unified Quality Assessment of In-the-Wild Videos with Mixed Datasets Training [20.288424566444224]
  We focus on automatically assessing the quality of in-the-wild videos in computer vision applications. To improve the performance of quality assessment models, we borrow intuitions from human perception. We propose a mixed datasets training strategy for training a single VQA model with multiple datasets.
  arXiv  Detail & Related papers  (2020-11-09T09:22:57Z)
• 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.