AI Paper Atlas

Research map / Detection and segmentation / CNN features

End-to-End Object Detection with Transformers

Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, Sergey Zagoruyko

ECCV 2020 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors

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 transformer encoder layers (0 to 6) (ablation)DETR R50 · COCO val 2017 (bbox, 300-epoch ablation schedule)AP: 36.7 -> 40.6Improved
add 12 encoder layers instead of 6 (ablation)DETR R50 · COCO val 2017 (bbox, 300-epoch ablation schedule)AP: 40.6 -> 41.6Improved
add FFN in transformer layers (ablation)DETR R50 · COCO val 2017 (bbox, 300-epoch ablation schedule)AP: drops 2.3 AP when removed (41.3M to 28.7M params)Improved
add spatial positional encodings (ablation)DETR R50 · COCO val 2017 (bbox, 300-epoch ablation schedule)AP: 32.8 -> 40.6Improved
pass sine positional encodings at every attention layer instead of once at input (ablation)DETR R50 · COCO val 2017 (bbox, 300-epoch ablation schedule)AP: 39.2 -> 40.6Improved
use spatial positional encodings in the encoder (ablation)DETR R50 · COCO val 2017 (bbox, 300-epoch ablation schedule)AP: 39.3 -> 40.6Improved
add GIoU loss to class+L1 (ablation)DETR R50 · COCO val 2017 (bbox, 300-epoch ablation schedule)AP: 35.8 -> 40.6Improved
add L1 loss to class+GIoU (ablation)DETR R50 · COCO val 2017 (bbox, 300-epoch ablation schedule)AP: 39.9 -> 40.6Improved
apply NMS to later decoder layer outputs (ablation)DETR R50 · COCO val 2017 (bbox, 300-epoch ablation schedule)APHurt
add decoder layers (first to last layer outputs) (ablation)DETR R50 · COCO val 2017 (bbox, 300-epoch ablation schedule)AP: +8.2/9.5 AP between first and last layerImproved
add random crop augmentationDETR · COCO val 2017 (bbox)AP: approximately 1 APImproved
longer schedule (500 vs 300 epochs)DETR · COCO val 2017 (bbox)AP: 40.6 -> 42.0Improved

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