AI Paper Atlas

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

DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLM

Yixuan Wu, Yizhou Wang, Shixiang Tang, Wenhao Wu, Tong He, Wanli Ouyang, Philip Torr, Jian Wu

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 32 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 DetToolChain to GPT-4V on COCO open-vocabulary detectionGPT-4V · COCO OVD NovelAP50: 2.3 -> 65.8Improved
add DetToolChain to GPT-4V on COCO val2017GPT-4V · COCO val2017AP: 0.3 -> 34.5Improved
add DetToolChain to GPT-4V on described object detectionGPT-4V · D-cube FULLAP: 16.3 -> 37.2Improved
add DetToolChain to GPT-4V on RefCOCOGPT-4V · RefCOCO valAccuracy@0.5: 25.48 -> 70.01Improved
add ruler marker (ablation)GPT-4V · COCO single object subsetmIoUp: 0.23 -> 0.52Improved
add compass marker for oriented objects (ablation)GPT-4V · HRSC2016mIoUp: 0.13 -> 0.47Improved
add compass marker for COCO small objects (ablation)GPT-4V · COCO small object subsetmIoUp: 0.16 -> 0.14No clear effect
add image split and zoom in (ablation)GPT-4V · COCO small object subsetmIoUp: 0.16 -> 0.46Improved
add convex hull marker and self-verification to ruler (ablation)GPT-4V · COCO occlusion subsetmIoUp: 0.43 -> 0.70Improved
use full DetToolChain instead of zero-shot CoT (ablation)GPT-4V · COCO single object subsetmIoUp: 0.25 -> 0.78Improved
use DetToolChain instead of multimodal CoT (ablation)GPT-4V · COCO multi-objects subsetmIoUp: 0.32 -> 0.64Improved
DetToolChain higher AP50 than AP75 on COCO val2017GPT-4V · COCO val2017AP75: AP75 31.5 vs DETR-R50 44.2Mixed

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