AI Paper Atlas

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

Griffon: Spelling out All Object Locations at Any Granularity with Large Language Models

Yufei Zhan, Yousong Zhu, Zhiyang Chen, Fan Yang, Ming Tang, Jinqiao Wang

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 23 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
put label before coordinates in the unified output representation (ablation)Griffon · MSCOCO val2017 (1 epoch pre-training)mAP: 17.8 -> 22.2Improved
add training-free localization confidence score (ablation)Griffon inference · MSCOCO val2017mAP: 20.9 -> 22.2Improved
add label (recognition) score on top of localization score (ablation)Griffon inference · MSCOCO val2017mAP: 22.2 -> 23.2Improved
add localization score only (ablation)Griffon inference · MSCOCO val2017AR100: 33.9 -> 33.0Hurt
pre-train Griffon on single-referent REC data only versus full mixtureGriffon-13B · RefCOCO+ valAcc@0.5: 83.3 -> 84.8Improved
use Griffon-13B for multi-category detection compared with other LVLMsLVLM detection · MSCOCO val2017mAP: approximately 0 -> 24.8Improved
Griffon-13B vs Faster R-CNN-R50 at same resolutiondetection · MSCOCO val2017AP_S: 4.6 -> 5.9 (AP_S), 26.3 vs 24.8 (mAP)Mixed
Griffon-13B versus Ferret-13B on merged-boxes phrase grounding testphrase grounding · Flickr30K Entities MERGED-BOXES testrecall: 84.8 vs 82.8Hurt

Later papers that compared with this method

1 later accepted paper reports Griffon-13B as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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