AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules

Zhi-Qi Cheng, Qi Dai, Alexander G. Hauptmann

ICCV 2023 · Large language models › Language, safety and interpretability · approach: Data and evaluation methodology · 30 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 rule-free chart component detection and extended embeddings with multi-task trainingT5 · ChartQA (test)relaxed accuracy: 41.04 -> 52.60Improved
add center-point detection module (ablation)chart component detection · EC400K Linechart-to-table score: 0.63 -> 0.97Improved
add grouping of centers and keypoints (ablation)chart component detection · EC400K Barchart-to-table score: 0.77 -> 0.95Improved
add appearance embedding to input encoding (ablation)TaPas · PlotQA-V1accuracy: 59.10 -> 74.20Improved
add chart component detection (CCD) to input (ablation)TaPas · PlotQA-V1accuracy: 52.30 -> 74.20Improved
add location embedding to input encoding (ablation)TaPas · PlotQA-V2accuracy: 51.20 -> 56.20Improved
add multi-task training on top of full pretraining mix (ablation)T5 · ChartQA (test)accuracy: 42.2 -> 52.6Improved
add chart-to-text data to the pretraining mix with multi-task (ablation)T5 · ChartQA (test)accuracy: 43.2 -> 52.6Improved
mix all datasets in multi-task training rather than sequential training (ablation)T5 · ChartQA (test)accuracy: 51.6 -> 52.6Improved
add CCD module (without multi-task) (ablation)T5 pretrained on PQA, finetuned on CQA · ChartQA (test)accuracy: 39.2 -> 39.6No clear effect
add CCD module (ablation)T5 · training costTPU hours: 13 -> 28Hurt
replace rule-based derendering with keypoint detectionChart-to-table · EC400KGPU hours: 57h -> 22hImproved

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