通过弱到强学习实现可泛化的视频质量评估
Generalizable Video Quality Assessment via Weak-to-Strong Learning
AI总结：
提出弱到强学习框架，结合同质/异质监督信号和迭代训练，无需人工标注即可提升视频质量评估的泛化能力。
摘要：
视频质量评估（VQA）旨在预测与人类视觉感知一致的视频感知质量，是量化视频处理流程中质量退化的基本工具。主流的VQA范式依赖于人工标注数据集的监督训练，尽管取得了显著进展，但在未见视频内容上仍存在泛化能力差的问题。本文探索弱到强（W2S）学习作为一种无需依赖人工标注数据集的新范式来推进VQA。我们首先提供经验证据，表明直接的W2S策略使强学生模型不仅能在域内基准上匹配其弱教师，还能在分布外（OOD）基准上超越教师，揭示了VQA中独特的弱到强效应。基于这一洞察，我们提出一个新颖框架，从两个方面增强W2S学习：（1）通过可学习排序公式整合来自不同VQA教师（包括现成VQA模型和合成失真模拟器）的同质和异质监督信号；（2）迭代W2S训练，其中每个强学生被回收作为后续循环的教师，逐步聚焦于困难案例。大量实验表明，我们的方法在域内和OOD基准上均达到最先进结果，尤其在OOD场景中表现突出。我们的发现强调W2S学习是打破标注障碍、实现视频质量评估可扩展泛化的原则性途径。我们的数据和代码将在https://github.com/clh124/W2S-VQA提供。
英文摘要：
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. In this work, we explore weak-to-strong (W2S) learning as a new paradigm for advancing VQA without reliance on 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 video quality assessment. Our data and code will be available at https://github.com/clh124/W2S-VQA.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
