Methods › General › Self-Supervised Learning › BYOL

Bootstrap Your Own Latent

BYOL

123 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

BYOL (Bootstrap Your Own Latent) is a new approach to self-supervised learning. BYOL’s goal is to learn a representation y_θ which can then be used for downstream tasks. BYOL uses two neural networks to learn: the online and target networks. The online network is defined by a set of weights θ and is comprised of three stages: an encoder f_θ, a projector g_θ and a predictor q_θ. The target network has the same architecture as the online network, but uses a different set of weights ξ. The target network provides the regression targets to train the online network, and its parameters ξ are an exponential moving average of the online parameters θ.

Given the architecture diagram on the right, BYOL minimizes a similarity loss between q_θ(z_θ) and sg(z′_ξ), where θ are the trained weights, ξ are an exponential moving average of θ and sg means stop-gradient. At the end of training, everything but f_θ is discarded, and y_θ is used as the image representation.

Source: Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning

Image credit: Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning

Source: Bootstrap Your Own Latent - A New Approach to...

In Syntology repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: listed only). The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:2601.10804) is about this method is not checked.

From the lookup's note on this name: The same name also belongs to “Bootstrap Your Own Latent (BYOL)”, a method in the paper “Bootstrap your own latent: A new approach to self-supervised Learning” (arXiv:2006.07733, 8,979 citations), which the lookup finds cited far more than the paper this answer is about (0 citations), so this answer may be about a different sense of the name. For arXiv:2006.07733: its page on this site · ask the lookup about it.

Origin paper of this answer, arXiv:2601.10804 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified (of 6 harvested samples). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 123 · with a code link: 63 · where Syntology ran a sample: 24 (20 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (24 of 123 tagged: 20 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument)

Page 1 of 2: papers 1 to 100 of 123, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 124 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Self-Supervised Learning79
Representation Learning53
Contrastive Learning36
Linear evaluation15
Data Augmentation14
Image Classification11
Semantic Segmentation7
Object Detection6
Transfer Learning6
image-classification6
object-detection6
Diversity5
Action Recognition4
Clustering4
Pseudo Label4
Time Series Analysis4
Depth Estimation3
Disentanglement3
Few-Shot Learning3
Segmentation3

Usage over time archive 2025-07-28

Papers per year tagged with BYOL: 2020 to 2025, peak 39 39 0 2020: 3 papers 2020 2021: 39 papers 2021 2022: 36 papers 2022 2023: 23 papers 2023 2024: 17 papers 2024 2025: 5 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (123 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Self-Supervised Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections