AI Paper Atlas

Research map / Detection and segmentation / CNN features

Detection Transformer with Stable Matching

Shilong Liu, Tianhe Ren, Jiayu Chen, Zhaoyang Zeng, Hao Zhang, Feng Li, Hongyang Li, Jun Huang, Hang Su, Jun Zhu, Lei Zhang

ICCV 2023 · Detection and segmentation › CNN features · approach: Efficient DETR query design · 76 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 position-supervised loss (IoU-based target for positive classification scores) (ablation)DINO · COCO val2017 (R50, 12 epochs)AP: 49.2 -> 49.8Improved
add position-modulated matching cost (ablation)DINO + position-supervised loss · COCO val2017 (R50, 12 epochs)AP: 49.8 -> 50.2Improved
add dense memory fusion (ablation)DINO + PSL + PMC · COCO val2017 (R50, 12 epochs)AP: 50.2 -> 50.4Improved
use simple memory fusion instead of dense fusion (ablation)DINO + PSL + PMC · COCO val2017 (R50, 12 epochs)AP: 50.2 -> 50.2No clear effect
add classification probability to the positive-example target (s*p) (ablation)position-supervised loss · COCO val2017 (R50, 12 epochs)AP: 49.2 -> 26.4Hurt
use convex target s^2 instead of concave s^0.5 (ablation)position-supervised loss · COCO val2017 (R50, 12 epochs)AP: 49.3 -> 49.6Improved
increase classification loss weight to 20.0 (ablation)position-supervised loss · COCO val2017 (R50, 12 epochs)AP: 50.2 -> 48.3Hurt
use position-modulated cost with f2=s^2 instead of s^0.5 (ablation)position-modulated cost · COCO val2017 (R50, 12 epochs)AP: 50.2 -> 48.8Hurt
apply stable matching to other DETR variantsDeformable-DETR, DAB-Deformable-DETR, H-DETR · COCO val2017 (R50, 12 epochs)AP: +1.3, +1.0, +0.6Improved
apply stable matching to MaskDINOMaskDINO · COCO val2017 instance segmentationmask AP / box AP: 41.4 -> 42.1 mask AP; 45.7 -> 47.0 box APImproved
apply stable matching to DINO with Swin-L at 12 epochsDINO · COCO val2017 (Swin-L)AP: 56.8 -> 57.7Improved

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