# D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement

arXiv: https://arxiv.org/abs/2410.13842 · HTML: https://mlsanity.com/paper/2410.13842/

## Key facts

- Cited by 74 papers in the map (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 41 of its 49 references that are in the map.
- First posted on arXiv 17 Oct 2024.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 30 of 41)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR](https://mlsanity.com/paper/2201.12329/) (2022)
- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation](https://mlsanity.com/paper/1905.08094/) (2019)
- [DN-DETR: Accelerate DETR Training by Introducing Query DeNoising](https://mlsanity.com/paper/2203.01305/) (2022)
- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [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)
- [CrowdHuman: A Benchmark for Detecting Human in a Crowd](https://mlsanity.com/paper/1805.00123/) (2018)
- [RTMDet: An Empirical Study of Designing Real-Time Object Detectors](https://mlsanity.com/paper/2212.07784/) (2022)
- [Distilling Object Detectors with Fine-grained Feature Imitation](https://mlsanity.com/paper/1906.03609/) (2019)
- [General Instance Distillation for Object Detection](https://mlsanity.com/paper/2103.02340/) (2021)
- [Distilling Object Detectors via Decoupled Features](https://mlsanity.com/paper/2103.14475/) (2021)
- [Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving](https://mlsanity.com/paper/1904.04620/) (2019)

## Built on by (most cited first, 30 of 74)

- [YOLOv12: Attention-Centric Real-Time Object Detectors](https://mlsanity.com/paper/2502.12524/) (2025)
- [RF-DETR: Neural Architecture Search for Real-Time Detection Transformers](https://mlsanity.com/paper/2511.09554/) (2025)
- [DEIM: DETR with Improved Matching for Fast Convergence](https://mlsanity.com/paper/2412.04234/) (2024)
- [Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models](https://mlsanity.com/paper/2606.03748/) (2026)
- [Real-Time Object Detection Meets DINOv3](https://mlsanity.com/paper/2509.20787/) (2025)
- [Improving Small Drone Detection Through Multi-Scale Processing and Data Augmentation](https://mlsanity.com/paper/2504.19347/) (2025)
- [Dome-DETR: DETR with Density-Oriented Feature-Query Manipulation for Efficient Tiny Object Detection](https://mlsanity.com/paper/2505.05741/) (2025)
- [Advanced Layout Analysis Models for Docling](https://mlsanity.com/paper/2509.11720/) (2025)
- [LINEA: Fast and Accurate Line Detection Using Scalable Transformers](https://mlsanity.com/paper/2505.16264/) (2025)
- [Edge-case Synthesis for Fisheye Object Detection: A Data-centric Perspective](https://mlsanity.com/paper/2507.16254/) (2025)
- [Uni-Parser Technical Report](https://mlsanity.com/paper/2512.15098/) (2025)
- [QuPAINT: Physics-Aware Instruction Tuning Approach to Quantum Material Discovery](https://mlsanity.com/paper/2602.17478/) (2026)
- [EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation](https://mlsanity.com/paper/2603.18739/) (2026)
- [MRC-DETR: An Adaptive Multi-Residual Coupled Transformer for Bare Board PCB Defect Detection](https://mlsanity.com/paper/2507.03386/) (2025)
- [DepTR-MOT: Unveiling the Potential of Depth-Informed Trajectory Refinement for Multi-Object Tracking](https://mlsanity.com/paper/2509.17323/) (2025)
- [Real-Time Oriented Object Detection Transformer in Remote Sensing Images](https://mlsanity.com/paper/2603.15497/) (2026)
- [A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helps](https://mlsanity.com/paper/2603.28182/) (2026)
- [MORE: A Multilingual Document Parsing Benchmark and Evaluation](https://mlsanity.com/paper/2607.02956/) (2026)
- [ContourFormer: Real-Time Contour-Based End-to-End Instance Segmentation Transformer](https://mlsanity.com/paper/2501.17688/) (2025)
- [DETRPose: Real-Time End-to-End Multi-Person Pose Estimation via Modified Transformer Decoder and Novel Denoising Keypoints](https://mlsanity.com/paper/2506.13027/) (2025)
- [High-Frequency Semantics and Geometric Priors for End-to-End Detection Transformers in Challenging UAV Imagery](https://mlsanity.com/paper/2507.00825/) (2025)
- [LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detection](https://mlsanity.com/paper/2512.05663/) (2025)
- [PARL: Position-Aware Relation Learning Network for Document Layout Analysis](https://mlsanity.com/paper/2601.07620/) (2026)
- [Le-DETR: Revisiting Real-Time Detection Transformer with Efficient Encoder Design](https://mlsanity.com/paper/2602.21010/) (2026)
- [RiO-DETR: DETR for Real-time Oriented Object Detection](https://mlsanity.com/paper/2603.09411/) (2026)
- [FB-CLIP: Fine-Grained Zero-Shot Anomaly Detection with Foreground-Background Disentanglement](https://mlsanity.com/paper/2603.19608/) (2026)
- [WUTDet: A 100K-Scale Ship Detection Dataset and Benchmarks with Dense Small Objects](https://mlsanity.com/paper/2604.07759/) (2026)
- [Rethinking Event-Based Object Detection through Representation-Level Temporal Aggregation and Model-Level Hypergraph Reasoning](https://mlsanity.com/paper/2605.08825/) (2026)
- [RT-SDGOD: Real-Time Single-Domain Generalized Object Detection](https://mlsanity.com/paper/2606.09367/) (2026)
- [CP-WSP: A Declarative CP-SAT Framework for Configurable Multi-Constraint Workforce Scheduling](https://mlsanity.com/paper/2607.05177/) (2026)

## Abstract (arXiv)

We introduce D-FINE, a powerful real-time object detector that achieves outstanding localization precision by redefining the bounding box regression task in DETR models. D-FINE comprises two key components: Fine-grained Distribution Refinement (FDR) and Global Optimal Localization Self-Distillation (GO-LSD). FDR transforms the regression process from predicting fixed coordinates to iteratively refining probability distributions, providing a fine-grained intermediate representation that significantly enhances localization accuracy. GO-LSD is a bidirectional optimization strategy that transfers localization knowledge from refined distributions to shallower layers through self-distillation, while also simplifying the residual prediction tasks for deeper layers. Additionally, D-FINE incorporates lightweight optimizations in computationally intensive modules and operations, achieving a better balance between speed and accuracy. Specifically, D-FINE-L / X achieves 54.0% / 55.8% AP on the COCO dataset at 124 / 78 FPS on an NVIDIA T4 GPU. When pretrained on Objects365, D-FINE-L / X attains 57.1% / 59.3% AP, surpassing all existing real-time detectors. Furthermore, our method significantly enhances the performance of a wide range of DETR models by up to 5.3% AP with negligible extra parameters and training costs. Our code and pretrained models: https://github.com/Peterande/D-FINE.