AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

InfoDet: A Dataset for Infographic Element Detection

Jiangning Zhu, Yuxing Zhou, Zheng Wang, Juntao Yao, Yima Gu, Yuhui Yuan, Shixia Liu

ICLR 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary 3D and world perception

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 grounded CoT (detected boxes plus text descriptions) over Direct promptingo4-mini · ChartQAPro overallenhanced relaxed accuracy: 63.2 -> 64.9Improved
add grounded CoT over Direct promptingo1 · ChartQAPro overallenhanced relaxed accuracy: 61.4 -> 64.1Improved
add grounded CoT over Direct promptingo3 · ChartQAPro overallenhanced relaxed accuracy: 60.6 -> 61.6Improved
use standard CoT or PoT promptingo1, o3, o4-mini · ChartQAPro overallenhanced relaxed accuracy: o4-mini 63.2 -> 62.5 (CoT), 59.7 (PoT)No clear effect
combine visual and textual prompts instead of visual only (ablation)grounded CoT on o1 · ChartQAPro overallenhanced relaxed accuracy: 62.8 -> 64.1Improved
combine visual and textual prompts instead of textual only (ablation)grounded CoT on o1 · ChartQAPro overallenhanced relaxed accuracy: 61.6 -> 64.1Improved
separate visual prompt into two layers (charts/HROs and texts) (ablation)grounded CoT on o1 · ChartQAPro overallenhanced relaxed accuracy: 62.3 -> 64.1Improved
add in-context examples to grounded CoT (ablation)grounded CoT on o1 · ChartQAPro overallenhanced relaxed accuracy: 64.1 -> 61.5Hurt
few-shot prompting with annotated example infographicsfoundation detectors · InfoDet element-levelAP: MQ-GLIP chart AP 13.5 -> 16.2No clear effect
fine-tune on full InfoDet training set instead of 4-shot (ablation)Co-DETR · InfoDet element-levelchart AP: 27.6 -> 88.2Improved
fine-tune traditional detector on InfoDet rather than zero-shot foundation modelFaster R-CNN vs DINO-X · InfoDet element-level chart APchart AP: 14.0 -> 78.9Improved
pre-train on InfoDet in addition to ImageNet-22K, Objects365, COCO (ablation)InternImage · Ricodetection score: 51.8 -> 53.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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