AI Paper Atlas

Research map / Detection and segmentation / CNN features

FeatAug-DETR: Enriching One-to-Many Matching for DETRs With Feature Augmentation

Rongyao Fang, Peng Gao, Aojun Zhou, Yingjie Cai, Si Liu, Jifeng Dai, Hongsheng Li

TPAMI 2024 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 27 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 FeatAug-FCDAB-DETR-DC5 (R50) · COCO val2017AP: 45.7 -> 47.1Improved
add FeatAug-FCDeform-DETR w/ tricks (R50, 12 epochs) · COCO val2017AP: 47.0 -> 48.7Improved
add FeatAug-FCDeform-DETR w/ tricks (Swin-L, 12 epochs) · COCO val2017AP: 54.5 -> 55.8Improved
add DataAug (N=2, 48 epochs)Deform-DETR w/ tricks (R50) · COCO val2017AP: 49.0 -> 50.0Improved
add FeatAug-FlipH-Deformable-DETR (Swin-L, 900 queries) · COCO val2017AP: 57.9 -> 58.3Improved
use spatial flip/crop instead of image resizing only in DataAug (ablation)Deform-DETR w/ tricks (R50) · COCO val2017AP: 48.9 -> 49.8Improved
increase DataAug augmentation count from N=2 to N=3 (ablation)Deform-DETR w/ tricks (R50, 36 epochs) · COCO val2017AP: 49.8 -> 49.4Hurt
add FeatAug-FC on top of FeatAug-Flip (ablation)Deform-DETR w/ tricks (R50, 24 epochs) · COCO val2017AP: 49.6 -> 49.9Improved
augment backbone features instead of encoder features (ablation)FeatAug-Flip on Deform-DETR w/ tricks (R50, 12 epochs) · COCO val2017AP: 46.5 -> 48.4Improved
use separate projector for cropped features (ablation)FeatAug-Crop on Deform-DETR w/ tricks (R50, 24 epochs) · COCO val2017AP: 49.2 -> 49.6Improved
add FeatAug-FCDeformable-DETR one-stage (R50, 50 epochs) · COCO val2017AP: 44.5 -> 46.3Improved
use FeatAug-Flip instead of FeatAug-FC with Hybrid Matching (ablation)H-Deformable-DETR (R50, 24 epochs) · COCO val2017AP: 50.1 -> 50.4Improved

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