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 accessAbstract
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.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.324 · Cited by 30,581
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_13 · Cited by 18,285 · cited 3×
“Object detection with transformer (DETR) [3] represents a shift from traditional CNN architectures to transformers.”
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · arXiv · doi:10.48550/arxiv.2005.12872 · Cited by 18,253
The Hungarian method for the assignment problem
Kuhn, H. W. (1955) · Naval Research Logistics Quarterly · doi:10.1002/nav.3800020109 · Cited by 13,120
DETRs Beat YOLOs on Real-time Object Detection
Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., & Chen, J. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01605 · Cited by 5,020 · cited 10×
“Despite attempts to improve query initialization using priors [18, 39, 43, 45], which enable more effective query distributions around objects.”
InfluentialYOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
Wang, C.-Y., Yeh, I.-H., & Mark Liao, H.-Y. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-72751-1_1 · Cited by 4,823
Multi-view 3D Object Detection Network for Autonomous Driving
Chen, X., Ma, H., Wan, J., Li, B., & Xia, T. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.691 · Cited by 3,450
TOOD: Task-aligned One-stage Object Detection
Feng, C., Zhong, Y., Gao, Y., Scott, M. R., & Huang, W. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00349 · Cited by 1,668 · cited 1×
“The O2M assignment strategy [10, 44] is widely adopted in traditional object detectors, and its super-vision can be formulated as follows: where N is the total number of targets, M i is the number of matches for the i -th target, ˆ y ij represents the j -th match for the i -th target, y i denotes…”
Zhang, X. (2017) · Encyclopedia of Machine Learning and Data Mining · doi:10.1007/978-1-4899-7687-1_79 · Cited by 1,434
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L. M., & Shum, H.-Y. (2022) · arXiv · Cited by 1,154 · cited 6×
“Despite attempts to improve query initialization using priors [18, 39, 43, 45], which enable more effective query distributions around objects.”
InfluentialVarifocalNet: An IoU-aware Dense Object Detector
Zhang, H., Wang, Y., Dayoub, F., & Sunderhauf, N. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00841 · Cited by 1,142
DN-DETR: Accelerate DETR Training by Introducing Query DeNoising
Li, F., Zhang, H., Liu, S., Guo, J., Ni, L. M., & Zhang, L. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01325 · Cited by 1,102
Conditional DETR for Fast Training Convergence
Meng, D., Chen, X., Fan, Z., Zeng, G., Li, H., Yuan, Y., Sun, L., & Wang, J. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00363 · Cited by 1,055
Monocular 3D Object Detection for Autonomous Driving
Chen, X., Kundu, K., Zhang, Z., Ma, H., Fidler, S., & Urtasun, R. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.236 · Cited by 1,019
DETRs with Collaborative Hybrid Assignments Training
Zong, Z., Song, G., & Liu, Y. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00621 · Cited by 592
Anchor DETR: Query Design for Transformer-Based Detector
Wang, Y., Zhang, X., Yang, T., & Sun, J. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i3.20158 · Cited by 482
Dynamic DETR: End-to-End Object Detection with Dynamic Attention
Dai, X., Chen, Y., Yang, J., Zhang, P., Yuan, L., & Zhang, L. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00298 · Cited by 456
Fast Convergence of DETR with Spatially Modulated Co-Attention
Gao, P., Zheng, M., Wang, X., Dai, J., & Li, H. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00360 · Cited by 345
Dense Distinct Query for End-to-End Object Detection
Zhang, S., Wang, X., Wang, J., Pang, J., Lyu, C., Zhang, W., Luo, P., & Chen, K. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00708 · Cited by 315
Jia, D., Yuan, Y., He, H., Wu, X., Yu, H., Lin, W., Sun, L., Zhang, C., & Hu, H. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01887 · Cited by 249
Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment
Chen, Q., Chen, X., Wang, J., Zhang, S., Yao, K., Feng, H., Han, J., Ding, E., Zeng, G., & Wang, J. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00610 · Cited by 238
Object Detection and Tracking for Autonomous Navigation in Dynamic Environments
Ess, A., Schindler, K., Leibe, B., & Van Gool, L. (2010) · The International Journal of Robotics Research · doi:10.1177/0278364910365417 · Cited by 191
Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETR
Li, F., Zeng, A., Liu, S., Zhang, H., Li, H., Zhang, L., & Ni, L. M. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01780 · Cited by 154
Detection Transformer with Stable Matching
Liu, S., Ren, T., Chen, J., Zeng, Z., Zhang, H., Li, F., Li, H., Huang, J. G., Su, H., Zhu, J., et al. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00597 · Cited by 110
MS-DETR: Efficient DETR Training with Mixed Supervision
Zhao, C., Sun, Y., Wang, W., Chen, Q., Ding, E., Yang, Y., & Wang, J. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01611 · Cited by 103
Cascade-DETR: Delving into High-Quality Universal Object Detection
Ye, M., Ke, L., Li, S., Tai, Y., Tang, C., Danelljan, M., & Yu, F. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00617 · Cited by 87
DN-DETR: Accelerate DETR Training by Introducing Query DeNoising
Li, F., Zhang, H., Liu, S., Guo, J., Ni, L. M., & Zhang, L. (2022) · arXiv · doi:10.48550/arxiv.2203.01305 · Cited by 57
Research works printed but not linked: 5
- Cai, 2024, Align-detr: Improving detr with simple iou-aware bce loss, BMVC
- Liu, 2022, Dab-detr: Dynamic anchor boxes are better queries for detr, ICLR
- Loshchilov, 2017, Decoupled weight decay regularization, ICLR
- Tian, 2022, Fully convolutional one-stage 3d object detection on lidar range images, NIPS
- Wang, 2023, Gold-yolo: Efficient object detector via gather-and-distribute mechanism, NeurIPS
Cited by
Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models
Jocher, G., Qiu, J., Liu, M., Lyu, S., Akyon, F. C., & Kalfaoglu, M. E. (2026) · arXiv · doi:10.48550/arxiv.2606.03748 · Cited by 16
“In parallel, DETR [5] cast detection as end-to-end set prediction, and its real-time descendants (RT-DETR [98], D-FINE [55], DEIM [21], RF-DETR [62]) have narrowed the accuracy gap with CNN-based detectors on standard benchmarks.”
Real-Time Object Detection on Edge Devices: A Fisheye Specific DFINE
Park, J., Lee, J., & Yong, Y. (2025) · 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw69036.2025.00573 · Cited by 4
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
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.