AI Paper Atlas

Research map / Detection and segmentation / CNN features

Conditional DETR for Fast Training Convergence

Depu Meng, Xiaokang Chen, Zejia Fan, Gang Zeng, Houqiang Li, Yuhui Yuan, Lei Sun, Jingdong Wang

ICCV 2021 · Detection and segmentation › CNN features · approach: Efficient DETR query design · 1,130 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 conditional cross-attention (conditional spatial query)DETR-R50, 50 epochs · COCO 2017 val (R50, 50 epochs)AP: 34.9 -> 40.9Improved
add conditional cross-attention at 50 epochsDETR-DC5-R50 · COCO 2017 val (DC5-R50, 50 epochs)AP: 36.7 -> 43.8Improved
add conditional cross-attention at 50 epochsDETR-R101 · COCO 2017 val (R101, 50 epochs)AP: 36.9 -> 42.8Improved
add conditional cross-attention at 50 epochsDETR-DC5-R101 · COCO 2017 val (DC5-R101, 50 epochs)AP: 38.6 -> 45.0Improved
train 108 epochs instead of 50Conditional DETR-R50 · COCO 2017 val (R50, 50 epochs)AP: 40.9 -> 43.0Improved
add learned or predicted reference points instead of s=(0,0) (ablation)Conditional DETR · COCO 2017 val (R50, 50 epochs)AP: 36.8 -> 40.9Improved
learn reference points as parameters instead of predicting from object query (ablation)Conditional DETR · COCO 2017 val (R50, 50 epochs)AP: 40.7 -> 40.9No clear effect
use full conditional spatial query instead of positional embedding only (ablation)Conditional DETR · COCO 2017 val (R50, 50 epochs)AP: 37.8 -> 40.9Improved
use full conditional spatial query instead of transformation only (ablation)Conditional DETR · COCO 2017 val (R50, 50 epochs)AP: 37.6 -> 40.9Improved
use transformation from decoder embedding f rather than content embedding in the query (CSQ-C) (ablation)Conditional DETR · COCO 2017 val (R50, 50 epochs)AP: 37.1 -> 40.9Improved
predict transformation from decoder embedding instead of self-attention output (ablation)Conditional DETR · COCO 2017 val (R50, 50 epochs)AP: 40.2 -> 40.9Improved
add conditional spatial query on top of focal loss and offset regression (ablation)Conditional DETR · COCO 2017 val (R50, 50 epochs)AP: 36.9 -> 40.9Improved

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