AI Paper Atlas

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

Multi-Label Zero-Shot Learning With Structured Knowledge Graphs

CVPR 2018 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 335 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
Use structured knowledge graph propagation (ablation)Proposed ML-ZSL model · NUS-1000 ML-ZSLF1: 28.1 -> 30.6Helped
Use structured knowledge graph propagation (ablation)Proposed generalized ML-ZSL model · NUS-1000 generalized ML-ZSLF1: 23.9 -> 24.2Helped
Use the proposed graph-based model instead of Fast0Tag (K=3)NUS-1000 ML-ZSL · NUS-1000 ML-ZSLF1: 27.2 -> 30.6Helped
Use the proposed graph-based model instead of Fast0Tag (K=10)NUS-1000 generalized ML-ZSL · NUS-1000 generalized ML-ZSLF1: 21.9 -> 24.2Helped
Use the proposed model instead of LogisticsMulti-label classifier · NUS-81F1: 43.9 -> 45.7Helped
Use the proposed model instead of LogisticsMulti-label classifier · MS-COCOF1: 66.9 -> 69.0Helped

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