AI Paper Atlas

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

Hierarchical Graph Attention Network for Few-Shot Visual-Semantic Learning

Chengxiang Yin, Kun Wu, Zhengping Che, Bo Jiang, Zhiyuan Xu, Jian Tang

ICCV 2021 · Vision-language and multimodal › Visual question answering · approach: Vision-language model VQA evaluation · 13 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 visual-specific relationship GNN (ablation)HGAT · Visual Genome-QAaccuracy: 76.10 -> 77.55; 82.14 -> 84.01; 63.99 -> 63.77; 66.30 -> 69.26Mixed
add semantic-specific relationship GNN (ablation)HGAT · Visual Genome-QAaccuracy: 76.10 -> 78.14; 82.14 -> 83.88; 63.99 -> 64.23; 66.30 -> 68.61Improved
add both visual- and semantic-specific GNNs (ablation)HGAT · Visual Genome-QAaccuracy: 76.10 -> 78.86; 82.14 -> 84.55; 63.99 -> 65.21; 66.30 -> 70.06Improved
add attention-based co-learning between modalities (ablation)HGAT · Visual Genome-QAaccuracy: 78.86 -> 79.56; 84.55 -> 86.10; 65.21 -> 66.62; 70.06 -> 72.13Improved
replace fully-connected label prediction with Stage-2 relation-aware GNNs (ablation)HGAT · Visual Genome-QAaccuracy: 77.47 -> 79.56; 83.26 -> 86.10; 64.90 -> 66.62; 70.03 -> 72.13Improved
semi-supervised use of unlabeled support samples (40% labeled)HGAT · Toronto COCO-QA5-way 5-shot accuracy: 66.09 -> 67.16Improved
semi-supervised use of unlabeled support samples (60% labeled)HGAT · Toronto COCO-QA5-way 5-shot accuracy: 69.83 -> 70.78Improved
semi-supervised use of unlabeled support samples (80% labeled)HGAT · Toronto COCO-QA5-way 5-shot accuracy: 73.12 -> 73.95Improved
unlabeled support samples drawn from other classes (distractors)HGAT · Toronto COCO-QA5-way 5-shot accuracy: 66.09 -> 64.25; 69.83 -> 68.94; 73.12 -> 73.01Hurt
HGAT instead of EGNN in few-shot VQAEGNN · Visual Genome-QAaccuracy: 77.67 -> 79.56; 83.26 -> 86.10; 64.07 -> 66.62; 70.87 -> 72.13Improved

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