AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering

Medhini Narasimhan, Svetlana Lazebnik, Alexander Schwing

NeurIPS 2018 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 63 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 assess candidate answers with a 2-layer GCN and top-3 predicted relations instead of retrieving one supporting factFVQA answer prediction · FVQAaccuracy @1: 69.35 vs 62.20Improved
add visual-concept features to question and entity representations (ablation)FVQA answer prediction · FVQAaccuracy @1: 10.32 -> 29.72Improved
filter candidate entities by the top-1 predicted relation (ablation)FVQA answer prediction with question and entity features · FVQAaccuracy @1: 10.32 -> 13.89Improved
add a 2-layer GCN before the MLP (ablation)FVQA answer prediction with question and entity features and relation @1 · FVQAaccuracy @1: 13.89 -> 14.12No clear effect
add a 2-layer GCN before the MLP (ablation)FVQA answer prediction with visual concepts and relation @1 · FVQAaccuracy @1: 50.36 -> 65.80Improved
add an MLP after the 2-layer GCN (ablation)FVQA answer prediction with visual concepts and relation @1 · FVQAaccuracy @1: 48.43 -> 65.80Improved
use 2 GCN layers instead of 1 (ablation)FVQA answer prediction with relation @3 · FVQAaccuracy @1: 57.89 -> 69.35Improved
use 2 GCN layers instead of 3 (ablation)FVQA answer prediction with relation @3 · FVQAaccuracy @1: 60.78 -> 69.35Improved
use top-3 rather than top-1 predicted relations (ablation)FVQA answer prediction with 2 GCN layers · FVQAaccuracy @1: 65.80 -> 69.35Improved
retrieve 100 rather than 50 facts (ablation)fact retrieval and downstream answer prediction · FVQAdownstream accuracy: 58.93 -> 69.35Improved
retrieve 150 rather than 100 facts (ablation)fact retrieval and downstream answer prediction · FVQAdownstream accuracy: 69.35 -> 68.23Hurt
use the ground-truth relation rather than a predicted relation (ablation)FVQA answer prediction with 2 GCN layers · FVQAaccuracy @1: 69.35 -> 72.97Improved

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