Project AURIONAI Use-Cases Research & Innovation
Google DeepMind
vision

BYOL

Self-supervised learning without negative pairs, from the paper "Bootstrap your own latent".

Google DeepMindGoogle DeepMindUK / USA
Figure from the BYOL paper: BYOL sketch summarizing the method by emphasizing the neural architecture.
Levelmodel
Classvision
Parametersnot in the notes
Contextnot in the notes
Released13 Jun 2020
Opennessunknown
Runs onnot in the notes
Statusactive

R&D Topics

Self-supervised visual representation learningproduced by

Identity

Developer
Google DeepMind
Family
not in the notes
Released
13 Jun 2020 sourcesannouncement page
Weights published
–
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
CNN
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
image
Output
not in the notes
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
unknown
Licence
not in the notes sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Lineage

The notes record no lineage for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/2006.07733 https://arxiv.org/abs/2006.07733
  2. github.com/open-mmlab/mmpretrain/tree/main/configs/byol https://github.com/open-mmlab/mmpretrain/tree/main/configs/byol
  3. arxiv.org/html/2006.07733 https://arxiv.org/html/2006.07733

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "BYOL", https://aurion.semai.id/models/byol/, records of October 2026.