AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection

Siheng Wang, Yanshu Li, Bohan Hu, Zhengdao Li, HaiboZhan, Linshan Li, Weiming Liu, Ruizhi Qian, Guangxin Wu, Hao Zhang, Jifeng Shen, Piotr Koniusz and 3 more

ICLR 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 12 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 hierarchical concept pool (DHCP) to baseline (ablation)DeCo-DETR baseline · OV-COCOAP50 novel: 30.4 -> 36.6Improved
add gradient isolation (PD-DuGi) (ablation)DeCo-DETR · OV-COCOAP50 novel: 36.6 -> 37.5Improved
add cosine annealed alignment/detection loss weighting (ablation)DeCo-DETR · OV-COCOAP50 novel: 37.5 -> 41.3Improved
add fine-grained prototypes (M2=4800) on top of coarse ones (ablation)DeCo-DETR · OV-COCOAP50 novel: 30.8 -> 41.3Improved
double fine-grained prototypes from 4800 to 9600 (ablation)DeCo-DETR · OV-COCOAP50 novel: 41.3 -> 41.5No clear effect
increase decoder queries from 300 to 2000 (ablation)DeCo-DETR · OV-COCOAP50 novel: 36.5 -> 41.3Improved
use 13B+ LVLM instead of 7B for region descriptions (ablation)DeCo-DETR (LLaVA-1.5) · OV-COCOAP50 novel: 30.1 -> 38.2Improved
scale LVLM beyond 13B (to Qwen2.5-VL 32B) (ablation)DeCo-DETR · OV-COCOAP50 novel: 38.2 -> 38.9No clear effect
remove text encoder at inference via prototype pool (vs Grounding DINO-T)DeCo-DETR · OV-COCOlatency / AP50 novel: 280ms -> 135ms; 42.1 -> 41.3 AP novelMixed
DeCo-DETR vs best prior on OV-COCO C-OVDDeCo-DETR · OV-COCO (C-OVD)AP50 novel: 46.2 (BIRDet) vs 44.9Hurt

Later papers that compared with this method

1 later accepted paper reports DeCo-DETR as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 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