atlas

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

Meta-Learning for Generalized Zero-Shot Learning

AAAI 2020 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 92 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 MAML-style meta-learning to WGAN generator and discriminator (ablation)conditional WGAN · CUB ZSLaccuracy: 59.1% -> 69.7%Helped
add meta-learning to WGAN (ablation)conditional WGAN · AWA2 ZSLaccuracy: 68.1% -> 77.5%Helped
use zero-shot task split (disjoint classes in meta-train/val) instead of MAML split (ablation)ZSML · AWA2 / CUB ZSLaccuracy: +1.7% / +2.4%Helped
add meta-learner to discriminator (ablation)ZSML · CUB / AWA2 ZSLaccuracy: 5.8% / 8.6% drop when removedHelped
add meta-learner to generator (ablation)ZSML · CUB / AWA2 ZSLaccuracy: 2.2% / 7.9% drop when removedHelped
ZSML vs prior generative GZSL methodsGZSL · aPYharmonic mean: 36.6 -> 40.9Helped
ZSML with 5 examples per seen class vs baselinesfew-shot GZSL · AwA2harmonic mean: 41.8 -> 49.1Helped
ZSML vs prior state of the artZSL · SUNper-class accuracyNo 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