AI Paper Atlas

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

Relational Knowledge Transfer for Zero-Shot Learning

Donghui Wang, Yanan Li, Yuetan Lin, Yueting Zhuang

AAAI 2016 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 94 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 RKT virtual unseen-class data to ESZSLESZSL · AwA Goog continuous attributesZSL accuracy: 67.07 -> 71.59Improved
add RKT virtual unseen-class data to ESZSLESZSL · AwA Goog Word2VecZSL accuracy: 54.43 -> 59.05Improved
add RKT virtual unseen-class data to ESZSLESZSL · CUB A[0,1]+WZSL accuracy: 42.14 -> 43.12Improved
add RKT to DAPDAP · AwA binary attributesZSL accuracy: 53.96 -> 58.69Improved
train semantic mapping only on augmented data (RKT AO) instead of original+augmented (ablation)RKT · AwA Word2VecZSL accuracy: +17.31Improved
train semantic mapping only on augmented data (RKT AO) (ablation)RKT · CUB attributesZSL accuracy: +6.14Improved
train semantic mapping only on augmented data (RKT AO) (ablation)RKT · Dogs Word2VecZSL accuracy: +5.78Improved
increase number of synthesized instances per class (ablation)RKT AO · AwA/CUB/DogsZSL accuracyMixed
vary sparse coding lambda (ablation)RKT · AwAZSL accuracyMixed

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