# Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training

arXiv: https://arxiv.org/abs/2004.06002 · HTML: https://mlsanity.com/paper/2004.06002/

## Key facts

- Cited by 103 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Apr 2020.

## Built on by (most cited first, 30 of 103)

- [Large Scale Visual Food Recognition](https://mlsanity.com/paper/2103.16107/) (2021)
- [QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection](https://mlsanity.com/paper/2103.09136/) (2021)
- [Focal and Efficient IOU Loss for Accurate Bounding Box Regression](https://mlsanity.com/paper/2101.08158/) (2021)
- [Localization Distillation for Dense Object Detection](https://mlsanity.com/paper/2102.12252/) (2021)
- [Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection](https://mlsanity.com/paper/2103.16368/) (2021)
- [A Review on Deep Learning in UAV Remote Sensing](https://mlsanity.com/paper/2101.10861/) (2021)
- [ACTIVE: Towards Highly Transferable 3D Physical Camouflage for Universal and Robust Vehicle Evasion](https://mlsanity.com/paper/2308.07009/) (2023)
- [Visible-Thermal Tiny Object Detection: A Benchmark Dataset and Baselines](https://mlsanity.com/paper/2406.14482/) (2024)
- [Semantics-Guided Contrastive Network for Zero-Shot Object detection](https://mlsanity.com/paper/2109.06062/) (2021)
- [Rank & Sort Loss for Object Detection and Instance Segmentation](https://mlsanity.com/paper/2107.11669/) (2021)
- [Localization Distillation for Object Detection](https://mlsanity.com/paper/2204.05957/) (2022)
- [Cascade-DETR: Delving into High-Quality Universal Object Detection](https://mlsanity.com/paper/2307.11035/) (2023)
- [RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generation](https://mlsanity.com/paper/2402.15853/) (2024)
- [Improving Object Detection by Label Assignment Distillation](https://mlsanity.com/paper/2108.10520/) (2021)
- [AFPN: Asymptotic Feature Pyramid Network for Object Detection](https://mlsanity.com/paper/2306.15988/) (2023)
- [MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection](https://mlsanity.com/paper/2309.14976/) (2023)
- [Deep learning for table detection and structure recognition: A survey](https://mlsanity.com/paper/2211.08469/) (2022)
- [Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art](https://mlsanity.com/paper/2309.04902/) (2023)
- [HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenes](https://mlsanity.com/paper/2409.19833/) (2024)
- [TNCR: Table Net Detection and Classification Dataset](https://mlsanity.com/paper/2106.15322/) (2021)
- [A Finite Element-Inspired Hypergraph Neural Network: Application to Fluid Dynamics Simulations](https://mlsanity.com/paper/2212.14545/) (2022)
- [Fracture Detection in Pediatric Wrist Trauma X-ray Images Using YOLOv8 Algorithm](https://mlsanity.com/paper/2304.05071/) (2023)
- [FAQ: Feature Aggregated Queries for Transformer-based Video Object Detectors](https://mlsanity.com/paper/2303.08319/) (2023)
- [Cross-Layer Feature Pyramid Transformer for Small Object Detection in Aerial Images](https://mlsanity.com/paper/2407.19696/) (2024)
- [Fracture Detection in Wrist X-ray Images Using Deep Learning-Based Object Detection Models](https://mlsanity.com/paper/2111.07355/) (2021)
- [Boosting R-CNN: Reweighting R-CNN Samples by RPN's Error for Underwater Object Detection](https://mlsanity.com/paper/2206.13728/) (2022)
- [TogetherNet: Bridging Image Restoration and Object Detection Together via Dynamic Enhancement Learning](https://mlsanity.com/paper/2209.01373/) (2022)
- [MPDIoU: A Loss for Efficient and Accurate Bounding Box Regression](https://mlsanity.com/paper/2307.07662/) (2023)
- [USIS16K: High-Quality Dataset for Underwater Salient Instance Segmentation](https://mlsanity.com/paper/2506.19472/) (2025)
- [FoodLogoDet-1500: A Dataset for Large-Scale Food Logo Detection via Multi-Scale Feature Decoupling Network](https://mlsanity.com/paper/2108.04644/) (2021)

## Abstract (arXiv)

Although two-stage object detectors have continuously advanced the state-of-the-art performance in recent years, the training process itself is far from crystal. In this work, we first point out the inconsistency problem between the fixed network settings and the dynamic training procedure, which greatly affects the performance. For example, the fixed label assignment strategy and regression loss function cannot fit the distribution change of proposals and thus are harmful to training high quality detectors. Consequently, we propose Dynamic R-CNN to adjust the label assignment criteria (IoU threshold) and the shape of regression loss function (parameters of SmoothL1 Loss) automatically based on the statistics of proposals during training. This dynamic design makes better use of the training samples and pushes the detector to fit more high quality samples. Specifically, our method improves upon ResNet-50-FPN baseline with 1.9% AP and 5.5% AP90 on the MS COCO dataset with no extra overhead. Codes and models are available at https://github.com/hkzhang95/DynamicRCNN.