AI Paper Atlas

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

Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding

Lingchen Meng, Xiyang Dai, Yinpeng Chen, Pengchuan Zhang, Dongdong Chen, Mengchen Liu, Jianfeng Wang, Zuxuan Wu, Lu Yuan, Yu-Gang Jiang

CVPR 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive object detection · 13 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
jointly train with dataset-aware queries and category-aligned language embeddings instead of training separatelyDetection Hub · COCOAP: 43.0 -> 45.3Improved
jointly train with dataset-aware queries and category-aligned language embeddings instead of training separatelyDetection Hub · Object365AP: 22.2 -> 23.2Improved
jointly train with dataset-aware queries and category-aligned language embeddings instead of training separatelyDetection Hub · Visual GenomeAP: 4.8 -> 5.7Improved
jointly train across the 11 UODB datasets using Detection HubDetection Hub · UODBAvg: 64.2 -> 71.0Improved
use dataset-aware sampling rather than image-level instance sampling (ablation)Detection Hub query adaptation · COCO, joint trainingAP: 14.5 -> 45.3Improved
use dataset-aware sampling rather than global category sampling (ablation)Detection Hub query adaptation · COCO, joint trainingAP: 39.8 -> 45.3Improved
increase adapted query count from 100 to 300 (ablation)Detection Hub · COCO, joint trainingAP: 42.3 -> 45.3Improved
add category-aligned embedding (ablation)Sparse-RCNN + Merge · COCO, separate trainingAP: 40.6 -> 40.1Hurt
add category-aligned embedding (ablation)Sparse-RCNN + Merge · COCO, joint trainingAP: 40.4 -> 43.1Improved
add dataset-aware query adaptation to the decoder (ablation)Sparse-RCNN + Merge with category-aligned embedding · COCO, joint trainingAP: 43.1 -> 44.0Improved
add dataset-aware query adaptation to the RPN (ablation)Detection Hub with decoder adaptation · COCO, joint trainingAP: 44.0 -> 45.6Improved
add dataset-aware query adaptation to the RPN (ablation)Detection Hub with decoder adaptation · Object365, joint trainingAP: 21.9 -> 23.5Improved

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