AI Paper Atlas

Research map / Detection and segmentation / CNN features

Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment

Qiang Chen, Xiaokang Chen, Jian Wang, Shan Zhang, Kun Yao, Haocheng Feng, Junyu Han, Errui Ding, Gang Zeng, Jingdong Wang

ICCV 2023 · Detection and segmentation › CNN features · approach: Efficient DETR query design · 341 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 group-wise one-to-many assignment with K groups of queries (ablation)Conditional DETR · COCO val2017 (12 epochs)mAP: 32.6 -> 34.8Improved
add separate self-attention per group (ablation)Group DETR · COCO val2017 (12 epochs)mAP: 34.8 -> 37.6Improved
use naive one-to-many assignment instead of group-wise (ablation)Conditional DETR · COCO val2017 (12 epochs)mAP: 32.6 -> 8.4Hurt
increase number of groups K up to 11 (ablation)Group DETR · COCO val2017 (12 epochs)mAPImproved
apply Group DETR to the encoder and decoder rather than decoder only (ablation)Conditional DETR · COCO val2017 (50 epochs)mAP: 41.5 -> 42.9Improved
give baseline longer training to match Group DETR time (ablation)Conditional DETR · COCO val2017mAP: 32.6 -> 34.4 vs Group DETR 37.6No clear effect
add Group DETR to Conditional DETR (12 epochs)Conditional DETR · COCO val2017 (12 epochs)mAP: 32.6 -> 37.6Improved
add Group DETR to DINO-4scaleDINO · COCO val2017mAP: 49.4 -> 50.1 (12e); 50.9 -> 51.3 (36e)Improved
add Group DETR to DINO-4scale-Swin-LDINO Swin-L · COCO val2017 (36 epochs)mAP: 58.0 -> 58.4Improved
gains shrink with longer training and stronger baselinesGroup DETR · COCO val2017mAP gain: Conditional DETR +5.0 (12e) -> +2.5 (50e); DN-DETR-DC5 +2.6 -> +0.5Mixed
combine Group DETR with DN-DETR denoising queriesDAB-DETR · COCO val2017 (12 epochs)mAP: +1.5 mAP over Group DETRImproved
increase DN-DETR denoising queries (ablation)DN-DETR · COCO val2017 (12 epochs)mAPNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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