# Semi-DETR: Semi-Supervised Object Detection with Detection Transformers

arXiv: https://arxiv.org/abs/2307.08095 · HTML: https://mlsanity.com/paper/2307.08095/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 50 references that are in the map.
- First posted on arXiv 16 Jul 2023.

## Builds on (most cited first, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR](https://mlsanity.com/paper/2201.12329/) (2022)
- [Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection](https://mlsanity.com/paper/1912.02424/) (2019)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [DN-DETR: Accelerate DETR Training by Introducing Query DeNoising](https://mlsanity.com/paper/2203.01305/) (2022)
- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection](https://mlsanity.com/paper/2006.04388/) (2020)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [End-to-End Semi-Supervised Object Detection with Soft Teacher](https://mlsanity.com/paper/2106.09018/) (2021)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [A Simple Semi-Supervised Learning Framework for Object Detection](https://mlsanity.com/paper/2005.04757/) (2020)
- [TOOD: Task-aligned One-stage Object Detection](https://mlsanity.com/paper/2108.07755/) (2021)
- [OTA: Optimal Transport Assignment for Object Detection](https://mlsanity.com/paper/2103.14259/) (2021)
- [Efficient DETR: Improving End-to-End Object Detector with Dense Prior](https://mlsanity.com/paper/2104.01318/) (2021)

## Built on by (most cited first, 27 of 27)

- [Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis](https://mlsanity.com/paper/2404.13686/) (2024)
- [AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving](https://mlsanity.com/paper/2403.17373/) (2024)
- [Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection](https://mlsanity.com/paper/2406.00510/) (2024)
- [Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection](https://mlsanity.com/paper/2404.01819/) (2024)
- [SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detection](https://mlsanity.com/paper/2407.01016/) (2024)
- [Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection](https://mlsanity.com/paper/2403.17387/) (2024)
- [Mixed Pseudo Labels for Semi-Supervised Object Detection](https://mlsanity.com/paper/2312.07006/) (2023)
- [UniFL: Improve Latent Diffusion Model via Unified Feedback Learning](https://mlsanity.com/paper/2404.05595/) (2024)
- [Semi-Supervised Object Detection with Uncurated Unlabeled Data for Remote Sensing Images](https://mlsanity.com/paper/2310.05498/) (2023)
- [Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformer](https://mlsanity.com/paper/2407.08460/) (2024)
- [Enhancing cross-domain detection: adaptive class-aware contrastive transformer](https://mlsanity.com/paper/2401.13264/) (2024)
- [Credible Teacher for Semi-Supervised Object Detection in Open Scene](https://mlsanity.com/paper/2401.00695/) (2024)
- [SemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-end Text Spotting](https://mlsanity.com/paper/2504.09966/) (2025)
- [A Comparative Benchmark of Real-time Detectors for Blueberry Detection towards Precision Orchard Management](https://mlsanity.com/paper/2509.20580/) (2025)
- [EgoPoseFormer v2: Accurate Egocentric Human Motion Estimation for AR/VR](https://mlsanity.com/paper/2603.04090/) (2026)
- [Auto-Labeling Data for Object Detection](https://mlsanity.com/paper/2506.02359/) (2025)
- [SS-DC: Spatial-Spectral Decoupling and Coupling Across Visible-Infrared Gap for Domain Adaptive Object Detection](https://mlsanity.com/paper/2507.12017/) (2025)
- [VFM-Guided Semi-Supervised Detection Transformer under Source-Free Constraints for Remote Sensing Object Detection](https://mlsanity.com/paper/2508.11167/) (2025)
- [Practical Insights into Semi-Supervised Object Detection Approaches](https://mlsanity.com/paper/2601.13380/) (2026)
- [Rethinking Scale Imbalance in Semi-supervised Object Detection for Aerial Images](https://mlsanity.com/paper/2310.14718/) (2023)
- [SGV3D:Towards Scenario Generalization for Vision-based Roadside 3D Object Detection](https://mlsanity.com/paper/2401.16110/) (2024)
- [Collaboration of Teachers for Semi-supervised Object Detection](https://mlsanity.com/paper/2405.13374/) (2024)
- [Unbiased Regression Loss for DETRs](https://mlsanity.com/paper/2410.22638/) (2024)
- [BCR-Net: Boundary-Category Refinement Network for Weakly Semi-Supervised X-Ray Prohibited Item Detection with Points](https://mlsanity.com/paper/2412.18918/) (2024)
- [SemiISP/SemiIE: Semi-Supervised Image Signal Processor and Image Enhancement Leveraging One-to-Many Mapping sRGB-to-RAW](https://mlsanity.com/paper/2504.02345/) (2025)
- [PPBoost: Progressive Prompt Boosting for Text-Driven Medical Image Segmentation](https://mlsanity.com/paper/2511.21984/) (2025)
- [FUSEP: A Multi-Center Benchmark for Diverse Tasks in Early Pregnancy Fetal Ultrasound Screening](https://mlsanity.com/paper/2608.04766/) (2026)

## Abstract (arXiv)

We analyze the DETR-based framework on semi-supervised object detection (SSOD) and observe that (1) the one-to-one assignment strategy generates incorrect matching when the pseudo ground-truth bounding box is inaccurate, leading to training inefficiency; (2) DETR-based detectors lack deterministic correspondence between the input query and its prediction output, which hinders the applicability of the consistency-based regularization widely used in current SSOD methods. We present Semi-DETR, the first transformer-based end-to-end semi-supervised object detector, to tackle these problems. Specifically, we propose a Stage-wise Hybrid Matching strategy that combines the one-to-many assignment and one-to-one assignment strategies to improve the training efficiency of the first stage and thus provide high-quality pseudo labels for the training of the second stage. Besides, we introduce a Crossview Query Consistency method to learn the semantic feature invariance of object queries from different views while avoiding the need to find deterministic query correspondence. Furthermore, we propose a Cost-based Pseudo Label Mining module to dynamically mine more pseudo boxes based on the matching cost of pseudo ground truth bounding boxes for consistency training. Extensive experiments on all SSOD settings of both COCO and Pascal VOC benchmark datasets show that our Semi-DETR method outperforms all state-of-the-art methods by clear margins. The PaddlePaddle version code1 is at https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/semi_det/semi_detr.