# RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer

arXiv: https://arxiv.org/abs/2407.17140 · HTML: https://mlsanity.com/paper/2407.17140/

## Key facts

- Cited by 91 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 24 Jul 2024.

## Builds on (most cited first, 8 of 8)

- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [PP-YOLOE: An evolved version of YOLO](https://mlsanity.com/paper/2203.16250/) (2022)
- [Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directions](https://mlsanity.com/paper/2112.11561/) (2021)
- [YOLOv6 v3.0: A Full-Scale Reloading](https://mlsanity.com/paper/2301.05586/) (2023)

## Built on by (most cited first, 30 of 91)

- [YOLOv12: Attention-Centric Real-Time Object Detectors](https://mlsanity.com/paper/2502.12524/) (2025)
- [D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement](https://mlsanity.com/paper/2410.13842/) (2024)
- [DEIM: DETR with Improved Matching for Fast Convergence](https://mlsanity.com/paper/2412.04234/) (2024)
- [YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception](https://mlsanity.com/paper/2506.17733/) (2025)
- [Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models](https://mlsanity.com/paper/2606.03748/) (2026)
- [RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervision](https://mlsanity.com/paper/2409.08475/) (2024)
- [Real-Time Object Detection Meets DINOv3](https://mlsanity.com/paper/2509.20787/) (2025)
- [FROSS: Faster-than-Real-Time Online 3D Semantic Scene Graph Generation from RGB-D Images](https://mlsanity.com/paper/2507.19993/) (2025)
- [Improving Small Drone Detection Through Multi-Scale Processing and Data Augmentation](https://mlsanity.com/paper/2504.19347/) (2025)
- [Advanced Layout Analysis Models for Docling](https://mlsanity.com/paper/2509.11720/) (2025)
- [ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing Supervision](https://mlsanity.com/paper/2602.14276/) (2026)
- [C3-OWD: A Curriculum Cross-modal Contrastive Learning Framework for Open-World Detection](https://mlsanity.com/paper/2509.23316/) (2025)
- [MHAF-YOLO: Multi-Branch Heterogeneous Auxiliary Fusion YOLO for accurate object detection](https://mlsanity.com/paper/2502.04656/) (2025)
- [PaQ-DETR: Learning Pattern and Quality-Aware Dynamic Queries for Object Detection](https://mlsanity.com/paper/2603.06917/) (2026)
- [Mcity Data Engine: Iterative Model Improvement Through Open-Vocabulary Data Selection](https://mlsanity.com/paper/2504.21614/) (2025)
- [Edge-case Synthesis for Fisheye Object Detection: A Data-centric Perspective](https://mlsanity.com/paper/2507.16254/) (2025)
- [From Orthomosaics to Raw UAV Imagery: Enhancing Palm Detection and Crown-Center Localization](https://mlsanity.com/paper/2509.12400/) (2025)
- [Referring Layer Decomposition](https://mlsanity.com/paper/2602.19358/) (2026)
- [EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation](https://mlsanity.com/paper/2603.18739/) (2026)
- [You Sense Only Once Beneath: Ultra-Light Real-Time Underwater Object Detection](https://mlsanity.com/paper/2504.15694/) (2025)
- [GeneVA: A Dataset of Human Annotations for Generative Text to Video Artifacts](https://mlsanity.com/paper/2509.08818/) (2025)
- [A Comparative Benchmark of Real-time Detectors for Blueberry Detection towards Precision Orchard Management](https://mlsanity.com/paper/2509.20580/) (2025)
- [Don't let the information slip away](https://mlsanity.com/paper/2602.22595/) (2026)
- [Real-Time Oriented Object Detection Transformer in Remote Sensing Images](https://mlsanity.com/paper/2603.15497/) (2026)
- [Towards Powerful and Practical Patch Attacks for 2D Object Detection in Autonomous Driving](https://mlsanity.com/paper/2508.10600/) (2025)
- [MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning](https://mlsanity.com/paper/2510.15026/) (2025)
- [FruitProm: Probabilistic Maturity Estimation and Detection of Fruits and Vegetables](https://mlsanity.com/paper/2510.24885/) (2025)
- [LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detection](https://mlsanity.com/paper/2512.05663/) (2025)
- [COMPOSE: Hypergraph Cover Optimization for Multi-view 3D Human Pose Estimation](https://mlsanity.com/paper/2601.09698/) (2026)
- [SurgAtt-Tracker: Online Surgical Attention Tracking via Temporal Proposal Reranking and Motion-Aware Refinement](https://mlsanity.com/paper/2602.20636/) (2026)

## Abstract (arXiv)

In this report, we present RT-DETRv2, an improved Real-Time DEtection TRansformer (RT-DETR). RT-DETRv2 builds upon the previous state-of-the-art real-time detector, RT-DETR, and opens up a set of bag-of-freebies for flexibility and practicality, as well as optimizing the training strategy to achieve enhanced performance. To improve the flexibility, we suggest setting a distinct number of sampling points for features at different scales in the deformable attention to achieve selective multi-scale feature extraction by the decoder. To enhance practicality, we propose an optional discrete sampling operator to replace the grid_sample operator that is specific to RT-DETR compared to YOLOs. This removes the deployment constraints typically associated with DETRs. For the training strategy, we propose dynamic data augmentation and scale-adaptive hyperparameters customization to improve performance without loss of speed. Source code and pre-trained models will be available at https://github.com/lyuwenyu/RT-DETR.