Research map / Detection and segmentation / CNN features
Dynamic DETR: End-to-End Object Detection With Dynamic Attention
Xiyang Dai, Yinpeng Chen, Jianwei Yang, Pengchuan Zhang, Lu Yuan, Lei Zhang
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 dynamic encoder (ablation) | DETR · COCO val2017 (1x ablation) | AP: 15.5 -> 24.1 | Improved |
| replace Deformable DETR encoder with dynamic encoder (ablation) | Deformable DETR · COCO val2017 (1x ablation) | AP: 37.2 -> 34.3 | Hurt |
| add dynamic encoder to dynamic decoder (ablation) | Dynamic DETR · COCO val2017 (1x ablation) | AP: 40.2 -> 42.9 | Improved |
| use dynamic decoder instead of Deformable DETR decoder (ablation) | Deformable DETR · COCO val2017 (1x ablation) | AP: 37.2 -> 40.2 | Improved |
| stack 6 dynamic encoders instead of 2 (ablation) | Dynamic DETR · COCO val2017 (1x ablation) | AP: 41.2 -> 42.9 | Improved |
| stack 6 dynamic decoders instead of 2 (ablation) | Dynamic DETR · COCO val2017 (1x ablation) | AP: 29.2 -> 42.9 | Improved |
| use 4 or 8 decoder heads instead of 2 (ablation) | Dynamic DETR · COCO val2017 (1x ablation) | AP: 42.5 -> 42.9 | No clear effect |
| increase decoder dimension from 512 to 2048 (ablation) | Dynamic DETR · COCO val2017 (1x ablation) | AP: 38.1 -> 42.9 | Improved |
| use 300 queries instead of 100 (ablation) | Dynamic DETR · COCO val2017 (1x ablation) | AP: 41.1 -> 42.9 | Improved |
| Dynamic DETR vs Deformable DETR convergence | Dynamic DETR · COCO val2017 (extended training) | AP: 47.2 mAP vs 45.3 mAP | Improved |
| Dynamic DETR vs best traditional detector under 1x schedule | Dynamic DETR · COCO val2017 (1x) | AP: 41.4 -> 42.9 | Improved |
Later papers that compared with this method
2 later accepted papers report Dynamic-DETR as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding (CVPR 2023 · better on 2 of 2 shared results)
- A Dynamic Dual-Processing Object Detection Framework Inspired by the Brain's Recognition Mechanism (ICCV 2023 · 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 7 of 7 on most shared results.
- Deformable DETR — Deformable DETR: Deformable Transformers for End-to-End Object Detection (ICLR 2021) · better on 3 of 3 shared results
- RepPoints v2 — RepPoints v2: Verification Meets Regression for Object Detection (NeurIPS 2020) · better on 2 of 3 shared results
- BorderDet — BorderDet: Border Feature for Dense Object Detection (ECCV 2020) · better on 2 of 2 shared results
- Sparse R-CNN — Sparse R-CNN: End-to-End Object Detection With Learnable Proposals (CVPR 2021) · better on 1 of 1 shared result
- FCOS — FCOS: Fully Convolutional One-Stage Object Detection (ICCV 2019) · better on 1 of 1 shared result
- Cascade-RCNN — Cascade R-CNN: Delving Into High Quality Object Detection (CVPR 2018) · better on 1 of 1 shared result
- Faster R-CNN — Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (TPAMI 2016) · 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
- Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity (ICLR 2022 · similarity 0.92)
- End-to-End Object Detection with Transformers (ECCV 2020 · similarity 0.90)
- Efficient Decoder-Free Object Detection with Transformers (ECCV 2022 · similarity 0.89)
- Lite DETR: An Interleaved Multi-Scale Encoder for Efficient DETR (CVPR 2023 · similarity 0.89)
- Not All Tokens Matter All The Time: Dynamic Token Aggregation Towards Efficient Detection Transformers (ICML 2025 · similarity 0.88)
- DETRs Beat YOLOs on Real-time Object Detection (CVPR 2024 · 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.
