AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Visual Concept-Metaconcept Learning

Chi Han, Jiayuan Mao, Chuang Gan, Josh Tenenbaum, Jiajun Wu

NeurIPS 2019 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded visual concept learning · 31 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
Jointly learn visual concepts and metaconcepts with VCMLCLEVR synonym generalization · CLEVRaccuracy: $100.0_{\pm0.0}$ vs. $66.3_{\pm1.4}$Improved
Jointly learn visual concepts and metaconcepts with VCMLCLEVR same-kind generalization · CLEVRaccuracy: $99.3_{\pm1.0}$ vs. $92.3_{\pm4.9}$Improved
Jointly learn visual concepts and metaconcepts with VCMLGQA synonym generalization · GQAaccuracy: $91.1_{\pm1.7}$ vs. $83.1_{\pm1.5}$Improved
Jointly learn visual concepts and metaconcepts with VCMLGQA same-kind generalization · GQAaccuracy: $69.1_{\pm1.7}$ vs. $68.2_{\pm4.0}$Improved
Jointly learn visual concepts and metaconcepts with VCMLCUB hypernym generalization · CUBaccuracy: $94.8_{\pm1.3}$ vs. $80.1_{\pm7.3}$Improved
Use VCML instead of NS-CLCUB meronym generalization · CUBaccuracy: $97.7_{\pm1.1}$ vs. $92.5_{\pm1.0}$Hurt
Include metaconcept questions during training (ablation)VCML few-shot visual concept learning · CUB held-out conceptstest accuracy: 78.5\% vs. 78.5\%Improved
Include metaconcept questions during training (ablation)NS-CL few-shot visual concept learning · CUB held-out conceptstest accuracy: 79.6\%Improved
Include metaconcept questions during training (ablation)MAC few-shot visual concept learning · CUB held-out conceptstest accuracy: 60.4\%Improved

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