AI Paper Atlas

Research map / Detection and segmentation / CNN features

DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Grounding

Shilong Liu, Shijia Huang, Feng Li, Hao Zhang, Yaoyuan Liang, Hang Su, Jun Zhu, Lei Zhang

AAAI 2023 · Detection and segmentation › CNN features · approach: Efficient DETR query design · 20 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
use dual queries to separate object localization and phrase localization (ablation)DQ-DETR · Flickr30k EntitiesCMAP50: 66.68 -> 69.86Improved
add text mask attention (ablation)DQ-DETR · Flickr30k EntitiesCMAP50: 66.68 -> 68.26Improved
add positional query sharing (ablation)DQ-DETR with dual queries and text mask attention · Flickr30k EntitiesCMAP50: 69.86 -> 70.63Improved
add text mask attention (ablation)DQ-DETR · Flickr30k EntitiesRecall@1: 75.44 -> 76.58Improved
add dual queries (ablation)DQ-DETR with text mask attention · Flickr30k EntitiesRecall@1: 76.58 -> 78.87Improved
add positional query sharing (ablation)DQ-DETR with dual queries and text mask attention · Flickr30k EntitiesRecall@1: 78.87 -> 79.16Improved
increase the number of queries to 200 (ablation)MDETR · Flickr30k EntitiesCMAP50: 61.49 -> 56.89Hurt
train with DQ-DETR rather than MDETRFlickr30k Entities, ResNet-101 pre-training · Flickr30k EntitiesCMAP50: +5.8 CMAP$_{50}$Improved
train with DQ-DETR rather than MDETRFlickr30k Entities, Any-Box protocol · Flickr30k EntitiesRecall@1: 82.5 -> 83.2Improved
train with DQ-DETR rather than MDETRCOCO detection · COCO detectionAP: 36.5 -> 41.2Improved
use DQ-DETR instead of OFA for referring expression comprehensionRefCOCO testA · RefCOCO testARecall@1: 90.67 -> 91.04Improved
use DQ-DETR instead of SeqTRRefCOCO testB · RefCOCO testBRecall@1: 83.59 -> 83.51Hurt

Later papers that compared with this method

4 later accepted papers report DQ-DETR as a baseline in their results tables; 4 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