AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments With Support Samples

Mahmoud Assran, Mathilde Caron, Ishan Misra, Piotr Bojanowski, Armand Joulin, Nicolas Ballas, Michael Rabbat

ICCV 2021 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 115 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 ME-max regularization (ablation)PAWS · ImageNet 1% labels, ResNet-50, 100 eptop-1 accuracy: 52.9 -> 63.8Improved
add ME-max regularization (ablation)PAWS · ImageNet 10% labels, ResNet-50, 100 eptop-1 accuracy: 73.6 -> 73.9Improved
add a prediction head during pre-training (ablation)PAWS · ImageNet 10% labels, ResNet-50, 100 eptop-1 accuracy: 74.2 -> 73.9No clear effect
add a prediction head during pre-training (ablation)PAWS · ImageNet 10% labels, ResNet-50, 200 eptop-1 accuracy: 75.2 -> 75.0No clear effect
enlarge the support set from 960x4 to 1000x16 images (ablation)PAWS · ImageNet 10% labels, ResNet-50, 100 eptop-1 accuracy: 72.0 -> 74.5Improved
sample 960 classes x 4 images instead of 448 classes x 8 (ablation)PAWS · ImageNet 10% labels, ResNet-50, 100 eptop-1 accuracy: 70.1 -> 72.0Improved
train 300 instead of 200 epochs (ablation)PAWS · ImageNet 10% labels, ResNet-50top-1 accuracy: 75.0 -> 75.5No clear effect
train 300 instead of 200 epochs (ablation)PAWS · ImageNet 10% labels, ResNet-50 (2x)top-1 accuracy: 77.8 -> 77.7No clear effect
fine-tune a classifier instead of nearest-neighbour classificationPAWS · ImageNet 1% labels, ResNet-50, 200 eptop-1 accuracy: 63.2 -> 66.1Improved
widen ResNet-50 from 1x to 4xPAWS · ImageNet 10% labels, 200 eptop-1 accuracy: 75.0 -> 79.0Improved
use PAWS 100 epochs instead of SwAV 800 epochsPAWS vs SwAV · ImageNet 1% labels, ResNet-50top-1 accuracy: +9.9%Improved
small-batch PAWS (batch 256, 8 GPUs) versus large batch with similar support (ablation)PAWS · ImageNet 10% labels, ResNet-50, 100 eptop-1 accuracy: 70.1 -> 70.2No clear effect

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