Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Cited by 296

The DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.

DEIM: DETR with Improved Matching for Fast Convergence

Open access
Huang, Shihua, Lu, Zhichao, Cun, Xiaodong, Yu, Yongjun, Zhou, Xiao, Shen, Xi · 2025 · 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Abstract

We introduce DEIM, an innovative and efficient training framework designed to accelerate convergence in real-time object detection with Transformer-based architectures (DETR). To mitigate the sparse supervision inherent in one-to-one (O2O) matching in DETR models, DEIM employs a Dense O2O matching strategy. This approach increases the number of positive samples per image by incorporating additional targets, using standard data augmentation techniques. While Dense O2O matching speeds up convergence, it also introduces numerous low-quality matches that could affect performance. To address this, we propose the Matchability-Aware Loss (MAL), a novel loss function that optimizes matches across various quality levels, enhancing the effectiveness of Dense O2O. Extensive experiments on the COCO dataset validate the efficacy of DEIM. When integrated with RT-DETR and D-FINE, it consistently boosts performance while reducing training time by 50%. Notably, paired with RT-DETRv2, DEIM achieves 53.2% AP in a single day of training on an NVIDIA 4090 GPU. Additionally, DEIM-trained real-time models outperform leading real-time object detectors, with DEIM-D-FINE-L and DEIM-D-FINE-X achieving 54.7% and 56.5% AP at 124 and 78 FPS on an NVIDIA T4 GPU, respectively, without the need for additional data. We believe DEIM sets a new baseline for advancements in real-time object detection. Our code and pre-trained models are available at https://www.shihuahuang.cn/DEIM/.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr52734.2025.01412

Cites

32 of 32 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 32 references

Research works printed but not linked: 5

  1. Cai, 2024, Align-detr: Improving detr with simple iou-aware bce loss, BMVC
  2. Liu, 2022, Dab-detr: Dynamic anchor boxes are better queries for detr, ICLR
  3. Loshchilov, 2017, Decoupled weight decay regularization, ICLR
  4. Tian, 2022, Fully convolutional one-stage 3d object detection on lidar range images, NIPS
  5. Wang, 2023, Gold-yolo: Efficient object detector via gather-and-distribute mechanism, NeurIPS

Cited by

See all 296

Metadata

Authors
Huang, S., Lu, Z., Cun, X., Yu, Y., Zhou, X., & Shen, X.
Venue
2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2025-06-10
Pages
15162-15171
ISSN
1063-6919 (ISSN-L)
OpenAlex
W4413147183
Cited by
296
References
32
FWCI
236.30
Type
conference paper
Language
en
Open access
green
Funders
Hefei Normal University

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: DEIM: DETR with Improved Matching for Fast Convergence. https://app.cochat.ai/papers/10.1109/cvpr52734.2025.01412
The paper
Huang, S., Lu, Z., Cun, X., Yu, Y., Zhou, X., & Shen, X. (2025). DEIM: DETR with Improved Matching for Fast Convergence. 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr52734.2025.01412

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.