Skip to content
AI News HubLIVE
Original source2 min read

Position: Unlabeled IS NOT Equal to No Human Supervision in Visual Learning

Summary

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. Different data curation schemes and training objectives embed substantially different human priors, so the blanket term “unsupervised” no longer captures these distinctions. The author advocates standardized disclosure practices to improve communication, fairer comparisons, and methodological diversity.

SourcearXiv Computer VisionAuthor: Dong Lao
Position: Unlabeled IS NOT Equal to No Human Supervision in Visual Learning
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 2 Sep 2026]

Title:Position: Unlabeled IS NOT Equal to No Human Supervision in Visual Learning

View a PDF of the paper titled Position: Unlabeled IS NOT Equal to No Human Supervision in Visual Learning, by Dong Lao

View PDF HTML (experimental)

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 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.

Comments: ICML 2026

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)

Cite as: arXiv:2609.03077 [cs.CV]

(or arXiv:2609.03077v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2609.03077

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Dong Lao [view email] [v1] Wed, 2 Sep 2026 18:45:41 UTC (923 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Position: Unlabeled IS NOT Equal to No Human Supervision in Visual Learning, by Dong Lao

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-09

Change to browse by:

cs cs.LG

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • “Unlabeled” does not mean an absence of human priors, since data curation and training objectives introduce human assumptions.
  • Top computer vision conferences have seen a sharp decline in papers titled “unsupervised” since 2021 despite continued field growth.
  • The paper calls for explicit disclosure of priors in data selection and learning objectives.
  • Standardized disclosure can improve academic communication and preserve methodological diversity.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

Position: Unlabeled IS NOT Equal to No Human Supervision in Visual Learning | AI News Hub