AI Paper Atlas

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

Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition

Xueting Zhang, Debin Meng, Henry Gouk, Timothy M. Hospedales

ICCV 2021 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Alignment-based few-shot metric learning · 67 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 a hand-crafted NIW prior to QDA (ablation)QDA · miniImageNet 5-shot (Conv-4)accuracy: 34.45 -> 71.40Improved
meta-learn the NIW prior instead of hand-crafting it (ablation)QDA with prior · miniImageNet 5-shot (Conv-4)accuracy: 71.40 -> 72.64Improved
meta-learn the NIW prior instead of hand-crafting it (ablation)QDA with prior · miniImageNet 5-shot (WRN)accuracy: 81.18 -> 84.28Improved
use QDA instead of LDA with meta-learned prior (ablation)MetaQDA · miniImageNet 1-shot (WRN)accuracy: 64.92 -> 67.83Improved
use QDA instead of LDA with meta-learned prior (ablation)MetaQDA · miniImageNet 5-shot (Conv-4)accuracy: 72.39 -> 72.64No clear effect
use Bayesian meta-learning instead of MAML (ablation)MetaQDA · miniImageNet 1-shot (Conv-4)accuracy: 54.33 -> 56.41Improved
use Bayesian meta-learning instead of MAML (ablation)MetaQDA · miniImageNet 5-shot (ResNet-18)accuracy: 77.82 -> 80.98Improved
use Bayesian meta-learning instead of MAML (ablation)MetaQDA · miniImageNet 1-shot (Conv-4)ECE: 52.75 -> 8.03Improved
use fully Bayesian instead of MAP inference (ablation)MetaQDA · miniImageNet 1-shot (Conv-4)ECE+TS: 2.75 -> 2.33Improved
use fully Bayesian instead of MAP inference (ablation)MetaQDA · miniImageNet 5-shot (WRN)ECE: 17.37 -> 15.86Improved
add MetaQDA classifier to URT featuresURT+PN · Meta-Datasetaverage accuracy overall: 73.7 -> 74.3Improved
replace SimpleShot NCC with MetaQDA in class-incremental learningNCC · miniImageNet FSCIL session 8accuracy: 32.26 -> 35.78Improved

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