AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

PAC-Bayes Meta-Learning With Implicit Task-Specific Posteriors

Cuong Nguyen, Thanh-Toan Do, Gustavo Carneiro

TPAMI 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Meta-augmentation and meta-objectives · 13 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 SImPa implicit posterior instead of ABML Gaussian posteriorSImPa vs ABML · Omniglot 5-way 1-shotaccuracy: 97.281 -> 98.352Improved
use SImPa instead of PLATIPUSSImPa vs PLATIPUS · mini-ImageNet 5-way 1-shot (4-block CNN)accuracy: 50.13 -> 51.72Improved
use SImPa instead of ABMLSImPa vs ABML · mini-ImageNet 5-way 1-shot (4-block CNN)accuracy: 45.00 -> 51.72Improved
use SImPa instead of Prototypical nets (trained 30-way)SImPa vs Prototypical nets · mini-ImageNet 5-way 5-shot (4-block CNN)accuracy: 68.20 -> 63.49Hurt
use SImPa with extracted features instead of LGM-NetSImPa vs LGM-Net · mini-ImageNet 5-way 1-shot (non-standard)accuracy: 69.13 -> 62.85Hurt
use SImPa with extracted features instead of LEOSImPa vs LEO · tiered-ImageNet 5-way 1-shotaccuracy: 66.33 -> 70.26Improved
use SImPa instead of MetaOptNetSImPa vs MetaOptNet · tiered-ImageNet 5-way 5-shotaccuracy: 81.75 -> 80.15Hurt
use SImPa instead of LEOSImPa vs LEO · mini-ImageNet 5-way 5-shot (non-standard)accuracy: 77.59 -> 77.65No clear effect
use SImPa instead of ABML/PLATIPUS/BMAML/MAML for calibrationSImPa · mini-ImageNet 1-shot (4-block CNN)ECE and MCEImproved
use SImPa instead of MAML, PLATIPUS, ABMLSImPa · multi-modal regressionMSEImproved
scale MAML to ResNet10 (about 5 million parameters)MAML · mini-ImageNetaccuracy: 89% train -> 42% testHurt

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