AI Paper Atlas

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

Plain-Det: A Plain Multi-Dataset Object Detector

Cheng Shi, Yuchen Zhu, Sibei Yang

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 10 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 class-aware query compositor (ablation)Plain-Det (C+L) · COCO+LVISmAP: 31.1 -> 36.5Improved
add CLIP text embedding calibration (subtract NULL embedding) (ablation)Plain-Det (C+L) · COCO+LVISmAP: 36.5 -> 37.8Improved
add dataset-specific partition head (ablation)Plain-Det (C+L) · COCO+LVISmAP: 31.6 -> 31.1Hurt
add hardness-indicated online sampler (ablation)Plain-Det · C+L+OmAP: 31.9 -> 35.0Improved
add Plain-Det to multi-dataset baselineDeformable-DETR (C+L+O+D) · 4-dataset mAPmAP: 40.0 -> 47.4Improved
add more datasets incrementally (L to L+C+O+D) (ablation)Plain-Det · 4-dataset mAPmAP: 29.8 -> 47.4Improved
multi-dataset training vs single-dataset trainingPlain-Det Def-DETR · COCO valAP: 45.6 -> 51.9Improved
use sparse queries instead of dense proposals for multi-dataset detection (ablation)Def-DETR / Sparse RCNN · COCO+LVISAPImproved
naive multi-dataset training without Plain-DetDeformable-DETR · 4-dataset mAPmAP: 43.2 -> 40.0Hurt
Plain-Det vs ScaleDet on ODinW zero-shotResNet50 detector · ODinW (5 datasets)mAP: 39.2 -> 46.1Improved

Later papers that compared with this method

1 later accepted paper reports PlainDet 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 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