AI Paper Atlas

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

Exploring Active Learning in Meta-Learning: Enhancing Context Set Labeling

Wonho Bae, Jing Wang, Danica J. Sutherland

ECCV 2024 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Meta-augmentation and meta-objectives · 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
select context set with Gaussian mixture centers instead of random pointsProtoNet · FC100 5-way 1-shot (unstratified)accuracy (%): 31.40 -> 35.03Improved
use uncertainty-based selection (Entropy or Margin) instead of randomMAML · MiniImageNet 5-way 5-shot (unstratified)accuracy (%): 58.84 -> 39.57 (Entropy)Hurt
use GMM selection instead of random for Baseline++Baseline++ · CUB 5-way 5-shot (test unstratified)accuracy (%): 79.57 -> 82.68Improved
use active selection at meta-train time (ablation)meta-learners · meta-training context selectionfinal predictor qualityHurt
use GMM instead of hybrid uncertainty+diversity methodsMAML · MiniImageNet 5-way 1-shot (train strat.)accuracy (%): 30.59 -> 33.34 vs k-means EntropyImproved
use GMM instead of k-means for selection (ablation)Baseline++ · CUB 5-wayaccuracy (points): +3.95 (1-shot), +11.79 (5-shot)Improved
use meta-learned features instead of SimCLR features for selection (ablation)GMM selection · few-shot classificationaccuracyImproved
use GMM selection in regression instead of randomMAML · Sine regression 3-shotMSE: 24.17 -> 18.09Improved
use GMM selection in cross-domain few-shotImageNet-pretrained ResNet18 · Places 1-shotaccuracy (%): 44.28 -> 60.01Improved
use GMM instead of ProbCover on cross-domain CUB 1-shotImageNet-pretrained ResNet18 · Cross-domain CUB 1-shotaccuracy (%): 62.13 -> 59.87Hurt

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