AI Paper Atlas

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

IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning

Pan Lu, Liang Qiu, Jiaqi Chen, Tony Xia, Yizhou Zhao, Wei Zhang, Zhou Yu, Xiaodan Liang, Song-Chun Zhu

NeurIPS 2021 · Vision-language and multimodal › Visual question answering · approach: Universal VQA models · 10 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
Pre-train the ResNet backbone on icon classification rather than natural images (ablation)Patch-TRM · IconQA validationaccuracy: 0.95-2.49%Improved
Add cross-modal attention instead of simple concatenation (ablation)Patch-TRM · IconQA validationaccuracy: up to 7%Improved
Add positional embeddings for ordered diagram patches (ablation)Patch-TRM · IconQA validationaccuracyImproved
Use patch features rather than the vision [CLS] output as the diagram feature (ablation)Patch-TRM · IconQA validationaccuracyImproved
Use the full pyramid patch set rather than coarse-grained patch cropping (ablation)Patch-TRM · IconQA validationaccuracy: 0.51% to 7.79%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