</> Code with Papers by Syntology

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...

Papers archive 2025-07-28

30 shown of 123, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

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