Methods › Computer Vision › Vision Transformers › MoCo v3
MoCo v3
Introduced by Xinlei Chen et al. in An Empirical Study of Training Self-Supervised Vision Transformers
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
MoCo v3 aims to stabilize training of self-supervised ViTs. MoCo v3 is an incremental improvement of MoCo v1/2. Two crops are used for each image under random data augmentation. They are encoded by two encoders f_q and fₖ with output vectors q and k. q behaves like a "query", where the goal of learning is to retrieve the corresponding "key". The objective is to minimize a contrastive loss function of the following form:
ℒ_𝓆=-log(exp(q ·k⁺ / τ))/(exp(q ·k⁺ / τ)+∑_(k⁻) exp(q ·k⁻ / τ))
This approach aims to train the Transformer in the contrastive/Siamese paradigm. The encoder f_q consists of a backbone (e.g., ResNet and ViT), a projection head, and an extra prediction head. The encoder fₖ has the back the backbone and projection head but not the prediction head. fₖ is updated by the moving average of f_q, excluding the prediction head.
Papers archive 2025-07-28
10 shown of 10, 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.
-
Task-Specific Knowledge Distillation from the Vision Foundation Model for Enhanced Medical Image Segmentation 10 Mar 2025 · 0 repositories · arXiv:2503.06976
-
Enhancing Contrastive Learning Inspired by the Philosophy of "The Blind Men and the Elephant" 21 Dec 2024 · 1 repository · arXiv:2412.16522
-
SRA: A Novel Method to Improve Feature Embedding in Self-supervised Learning for Histopathological Images 23 Oct 2024 · 0 repositories · arXiv:2410.17514
-
Improving Visual Prompt Tuning for Self-supervised Vision Transformers 8 Jun 2023 · 1 repository · arXiv:2306.05067Syntology ran 4 of 4 samples · 0 unverified
-
Internet Explorer: Targeted Representation Learning on the Open Web 27 Feb 2023 · 1 repository · arXiv:2302.14051
-
Pretraining the Vision Transformer using self-supervised methods for vision based Deep Reinforcement Learning 22 Sep 2022 · 1 repository · arXiv:2209.10901
-
Fast-MoCo: Boost Momentum-based Contrastive Learning with Combinatorial Patches 17 Jul 2022 · 1 repository · arXiv:2207.08220Syntology ran 1 of 4 samples · 3 unverified · 4 pointer-only (licence)
-
OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework 7 Feb 2022 · 4 repositories · arXiv:2202.03052Syntology ran 1 of 1 samples · 0 unverified
-
Self-Supervised Learning with Swin Transformers 10 May 2021 · 6 repositories · arXiv:2105.04553
-
An Empirical Study of Training Self-Supervised Vision Transformers 5 Apr 2021 · 9 repositories · arXiv:2104.02057Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 42 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
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
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