立场论文：无标签不等于无人类监督的视觉学习

AI 摘要

这篇立场论文认为，视觉学习中无标签并不等于无人类监督，因为数据整理方案和训练目标中嵌入了大量人类先验。作者指出，当前“无监督”术语过于笼统，掩盖了不同方法间的差异，并观察到自2021年以来CV顶会中标题含“无监督”的论文数量下降。他们呼吁社区明确披露数据选择和训练目标中的先验，以改进学术交流、确保公平比较并保留方法论多样性。

正文节选

Position: Unlabeled No Human Supervision in Visual Learning Abstract 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 t

发布时间：2026-09-04 12:00

抓取时间：2026-09-04 12:21

来源机构：arXiv