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
把「弱到强学习」当作绕开人工标注的通用范式：用现成 VQA 模型与合成失真模拟器作为弱教师，通过 learn-to-rank 融合异构监督信号，并迭代地把强学生回收为教师，可直接迁移到其他缺乏标注的低层视觉任务（如去噪、超分的主观质量预测）。
原文依据 we explore weak-to-strong (W2S) learning as a new paradigm for advancing VQA without reliance on human-labeled datasets
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论视频质量评估（VQA）旨在预测与人类视觉感知相一致视频感知质量，是量化视频处理流程中各环节质量退化的基础工具。主流的 VQA 范式依赖人工标注数据集进行监督训练，尽管已取得显著进展，但其对未见视频内容的泛化能力仍然较差。本文探索将弱到强（W2S）学习作为一种新范式，在不依赖人工标注数据集的前提下推进 VQA。我们首先给出经验性证据：一种直接的 W2S 策略可使强学生模型不仅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，从而揭示出 VQA 中一种独特的弱到强效应。基于这一发现，我们提出一个新框架，从两方面增强 W2S 学习：（1）通过学习排序（learn-to-rank）形式，融合来自多种 VQA 教师——包括现成的 VQA 模型与合成失真模拟器——的同质与异质监督信号；（2）迭代式 W2S 训练，每一轮中的强学生在下一次循环中被回收为教师，从而逐步聚焦于困难样本。大量实验表明，本方法在域内与 OOD 基准上均取得最优结果，且在 OOD 场景下提升尤为显著。我们的发现表明，W2S 学习是突破标注壁垒、实现视频质量评估可扩展泛化的一条有原则的路径。
英文原文摘要 1589 字符
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.