立场：视觉学习中，未标记数据并不等同于无人类监督

中文摘要 AI 辅助

本立场论文指出，在视觉学习中，缺少标签并不意味着缺少人类监督，并呼吁研究界更明确地识别监督来源。近期许多计算机视觉方法基于从大规模未标记数据中学习到的表示构建，因此被归在“无监督”这一统称下。然而，不同的数据整理方案和训练目标嵌入了模型所依赖的截然不同的人类先验，我们认为“无监督”这一统称已无法体现这些差异。这种模糊性使得在不同假设下开展的无监督学习研究更难比较，这与2021年以来旗舰计算机视觉会议中标题含“无监督”的论文数量大幅下降的情况相吻合，尽管该领域仍在持续发展。我们完全认可预训练是现代计算机视觉的强大基础，但倡导社区层面为提升概念清晰度而努力：鼓励作者披露数据选择和学习目标中的先验，并明确学习流程的哪些组件依赖于哪些假设。标准化披露实践可改善学术交流、确保更公平的比较，并保留无监督学习的方法多样性。

英文摘要

This position paper argues that the absence of labels does not imply the absence of human supervision in visual learning, and urges the research community to identify sources of supervision more explicitly. Many recent methods in computer vision build upon representations learned from large-scale unlabeled data, and are therefore grouped under the same umbrella term ``unsupervised.'' However, different data curation schemes and training objectives embed substantially different human priors on which models rely, and we argue that one ``unsupervised'' umbrella term is no longer capturing these distinctions. This ambiguity makes it harder to compare unsupervised learning research conducted under different assumptions, coinciding with a sharp decline in papers titled with ``unsupervised'' in flagship computer vision conferences since 2021, despite continued growth of the field. While we fully embrace pre-training as a strong foundation for modern computer vision, we advocate for a community-level effort toward greater conceptual clarity: authors are encouraged to disclose priors in data selection and learning objectives, and to specify which components of a learning pipeline depend on which assumptions. Standardized disclosure practices can improve academic communication, ensure fairer comparisons, and preserve methodological diversity in unsupervised learning.

发表机构

• Louisiana State University（路易斯安那州立大学）

机构由 AI 辅助整理，请以论文原文为准。

补充信息

备注

ICML 2026