arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.00643cs.CV
收藏

位置:视觉处理的评估应以人类为中心,而非以指标为中心

Evaluation of Visual Processing Should Be Human-Centered, Not Metric-Centered

Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(深圳先进技术研究院,中国科学院);The University of Hong Kong(香港大学);INSAIT, Sofia University ``St. Kliment Ohridski''(INSAIT,索菲亚大学『圣克莱孟·奥赫里迪斯』);Shenzhen Loop Area Institute(深圳河套学院);The Chinese University of Hong Kong(香港中文大学);University of the Chinese Academy of Sciences(中国科学院大学);Fudan University(复旦大学);Shenzhen University of Advanced Technology(深圳先进技术大学);Shanghai AI Laboratory(上海人工智能实验室)

Fanghua Yu, Jinfan Hu, Zhiyuan You, Xiang Yin, Hongyu An, Xinqi Lin, Chao Dong, Jinjin Gu

AI总结:

本文主张视觉处理评估应转向以人类为中心的方法,强调情境感知和细致评估,以更准确反映人类感知和用户需求。

摘要:

本文主张现代视觉处理系统评估应不再主要由单一指标图像质量评估基准驱动,特别是在生成式和感知导向方法的时代。图像恢复体现了这种分歧:虽然客观IQA指标能够实现可重复、可扩展的评估,但它们日益偏离人类感知和用户偏好。我们认为这种不匹配可能会限制创新并误导视觉处理任务的研究进展。与其完全摒弃指标,本文呼吁重新平衡评估范式,倡导更加以人类为中心、情境感知和细致的视觉模型结果评估方法。

英文摘要:

This position paper argues that the evaluation of modern visual processing systems should no longer be driven primarily by single-metric image quality assessment benchmarks, particularly in the era of generative and perception-oriented methods. Image restoration exemplifies this divergence: while objective IQA metrics enable reproducible, scalable evaluation, they have increasingly drifted apart from human perception and user preferences. We contend that this mismatch risks constraining innovation and misguiding research progress across visual processing tasks. Rather than rejecting metrics altogether, this paper calls for a rebalancing of evaluation paradigms, advocating a more human-centered, context-aware, and fine-grained approach to assessing the visual models' outcomes.

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。

↑