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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add class-aware query compositor (ablation) | Plain-Det (C+L) · COCO+LVIS | mAP: 31.1 -> 36.5 | Improved |
| add CLIP text embedding calibration (subtract NULL embedding) (ablation) | Plain-Det (C+L) · COCO+LVIS | mAP: 36.5 -> 37.8 | Improved |
| add dataset-specific partition head (ablation) | Plain-Det (C+L) · COCO+LVIS | mAP: 31.6 -> 31.1 | Hurt |
| add hardness-indicated online sampler (ablation) | Plain-Det · C+L+O | mAP: 31.9 -> 35.0 | Improved |
| add Plain-Det to multi-dataset baseline | Deformable-DETR (C+L+O+D) · 4-dataset mAP | mAP: 40.0 -> 47.4 | Improved |
| add more datasets incrementally (L to L+C+O+D) (ablation) | Plain-Det · 4-dataset mAP | mAP: 29.8 -> 47.4 | Improved |
| multi-dataset training vs single-dataset training | Plain-Det Def-DETR · COCO val | AP: 45.6 -> 51.9 | Improved |
| use sparse queries instead of dense proposals for multi-dataset detection (ablation) | Def-DETR / Sparse RCNN · COCO+LVIS | AP | Improved |
| naive multi-dataset training without Plain-Det | Deformable-DETR · 4-dataset mAP | mAP: 43.2 -> 40.0 | Hurt |
| Plain-Det vs ScaleDet on ODinW zero-shot | ResNet50 detector · ODinW (5 datasets) | mAP: 39.2 -> 46.1 | Improved |
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.
- DroneDINO: Towards Heterogeneous Routed Mixture of Experts for Drone-based Unified Object Detection (ICML 2026 · better on 1 of 1 shared result)
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.
- ScaleDet — ScaleDet: A Scalable Multi-Dataset Object Detector (CVPR 2023) · better on 4 of 4 shared results
- Sparse RCNN — Sparse R-CNN: End-to-End Object Detection With Learnable Proposals (CVPR 2021) · better on 1 of 1 shared result
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
- End-to-End Object Detection with Transformers (ECCV 2020 · similarity 0.89)
- Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity (ICLR 2022 · similarity 0.89)
- MS-DETR: Efficient DETR Training with Mixed Supervision (CVPR 2024 · similarity 0.88)
- Open-Det: An Efficient Learning Framework for Open-Ended Detection (ICML 2025 · similarity 0.87)
- Uni$^2$Det: Unified and Universal Framework for Prompt-Guided Multi-dataset 3D Detection (ICLR 2025 · similarity 0.87)
- Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models (NeurIPS 2025 · similarity 0.87)
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.
