AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Fast-MoCo: Boost Momentum-Based Contrastive Learning with Combinatorial Patches

Yuanzheng Ci, Chen Lin, Lei Bai, Wanli Ouyang

ECCV 2022 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Contrastive versus non-contrastive theory · 23 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add combinatorial patches (divide, encode, combine) (ablation)MoCo v3 · ImageNet-1k linear eval (100 epochs)top-1 accuracy: 70.3 -> 73.5Improved
combine patch embeddings after encoding instead of combining images before encoding (ablation)Fast-MoCo · ImageNet-1k linear eval (100 epochs)top-1 accuracy: 71.8 -> 73.5Improved
divide image into non-overlapping patches instead of random sampling (ablation)Fast-MoCo · ImageNet-1k linear eval (100 epochs)top-1 accuracy: 72.9 -> 73.5Improved
use 6 combined pairs per image instead of 2 (ablation)Fast-MoCo · ImageNet-1k linear eval (100 epochs)top-1 accuracy: 72.6 -> 73.5 (4 pairs: 73.3)Improved
average patch embeddings instead of max (ablation)Fast-MoCo · ImageNet-1k linear eval (100 epochs)top-1 accuracy: 64.6 -> 73.5Improved
use a different augmented view for the target (ablation)Fast-MoCo · ImageNet-1k linear eval (100 epochs)top-1 accuracy: 48.5 -> 73.5Improved
add multi-crop (ablation)Fast-MoCo · ImageNet-1k linear eval (100 epochs)top-1 accuracy: 73.5 -> 74.2Improved
add combinatorial patchesNNCLR · ImageNet-1k linear eval (100 epochs)top-1 accuracy: 69.4 -> 72.5Improved
add combinatorial patchesBYOL · ImageNet-1k linear eval (100 epochs)top-1 accuracy: 66.5 -> 73.6Improved
add combinatorial patchesSimSiam · ImageNet-1k linear eval (100 epochs)top-1 accuracy: 68.1 -> 71.7Improved
add combinatorial patches with AdamW optimizerMoCo v3 · ImageNet-1k linear eval (100 epochs)top-1 accuracy: 69.3 -> 71.7Improved
train longerFast-MoCo · ImageNet-1k linear evaltop-1 accuracy: 73.5 -> 75.1 -> 75.5 (100, 200, 400 epochs)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy