AI Paper Atlas

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

Deep Reference Priors: What is the best way to pretrain a model?

Yansong Gao, Rahul Ramesh, Pratik Chaudhari

ICML 2022 · Label-efficient and robust learning › Semi-supervised learning · approach: Self-training theory · 1 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
Use a discrete reference prior with unlabeled target data and labeled source data instead of fine-tuningCIFAR-100 transfer learning · Vehicles 2 → Vehicles 1accuracy: 66% -> 86%Improved
Use source data and unlabeled target data for transfer without target labelsMNIST transfer learning · Target digits 5–9, 0 labeled target samplesaccuracy: 86.6 -> 87.4Improved
Use EMA on particle weights (ablation)Deep Reference Prior · CIFAR-10, 50 labeled samplesaccuracy: 82.36 -> 85.45Improved
Vary prior order from 2 to 3, 4, or 5 (ablation)Deep Reference Prior · CIFAR-10, 1000 labeled samplesaccuracy: 91.76; 90.53; 91.51; 91.36No clear effect
Vary particle count from 4 to 2, 8, or 16 (ablation)Deep Reference Prior · CIFAR-10, 1000 labeled samplesaccuracy: 91.3; 91.76; 89.79; 90.72No clear effect
Remove the stop-gradient for weak-augmentation predictions (ablation)Deep Reference Prior · CIFAR-10, 250 labeled samplesaccuracy: 92.13 -> 10Hurt
Do not use Jensen's inequality to upper-bound the entropy (ablation)Deep Reference Prior · CIFAR-10, 250 labeled samplesaccuracy: 92.13 -> 86.55Hurt
Remove probability-threshold masking (ablation)Deep Reference Prior · CIFAR-10, 250 labeled samplesaccuracy: 92.13 -> 92.35No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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