Metraipolis › archive › dc_ce354507773e
Position: Unlabeled IS NOT Equal to No Human Supervision in Visual Learning — arXiv:2609.03077
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.03077
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T02:08:31.814Z
- SHA-256 of the archived text
57ae972821a85f64e758d3e36e968c6c0ebf4730a7b11553b673fd4399161e24- Stable URL of this page
https://metraipolis.com/documento/dc_ce354507773e
How to cite
Position: Unlabeled IS NOT Equal to No Human Supervision in Visual Learning — arXiv:2609.03077 — arXiv (en), https://arxiv.org/abs/2609.03077 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce354507773e (Metraipolis archive dc_ce354507773e, sha256 57ae972821a85f64e758d3e36e968c6c0ebf4730a7b11553b673fd4399161e24)
BibTeX
@misc{dcce354507773e,
title = {Position: Unlabeled IS NOT Equal to No Human Supervision in Visual Learning — arXiv:2609.03077},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.03077},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce354507773e; sha256 57ae972821a85f64e758d3e36e968c6c0ebf4730a7b11553b673fd4399161e24},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03077. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.LG). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.03077 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T01:47:25.598Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).