# DynamicDet: A Unified Dynamic Architecture for Object Detection

arXiv: https://arxiv.org/abs/2304.05552 · HTML: https://mlsanity.com/paper/2304.05552/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 60 references that are in the map.
- First posted on arXiv 12 Apr 2023.

## Builds on (most cited first, 30 of 48)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Res2Net: A New Multi-scale Backbone Architecture](https://mlsanity.com/paper/1904.01169/) (2019)
- [3DSSD: Point-based 3D Single Stage Object Detector](https://mlsanity.com/paper/2002.10187/) (2020)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [CSPNet: A New Backbone that can Enhance Learning Capability of CNN](https://mlsanity.com/paper/1911.11929/) (2019)
- [BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework](https://mlsanity.com/paper/2205.13790/) (2022)
- [SkipNet: Learning Dynamic Routing in Convolutional Networks](https://mlsanity.com/paper/1711.09485/) (2017)
- [NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection](https://mlsanity.com/paper/1904.07392/) (2019)
- [YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications](https://mlsanity.com/paper/2209.02976/) (2022)
- [Scaled-YOLOv4: Scaling Cross Stage Partial Network](https://mlsanity.com/paper/2011.08036/) (2020)

## Built on by (most cited first, 15 of 15)

- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [AiluRus: A Scalable ViT Framework for Dense Prediction](https://mlsanity.com/paper/2311.01197/) (2023)
- [AFter: Attention-based Fusion Router for RGBT Tracking](https://mlsanity.com/paper/2405.02717/) (2024)
- [You Only Look Once at Anytime (AnytimeYOLO): Analysis and Optimization of Early-Exits for Object-Detection](https://mlsanity.com/paper/2503.17497/) (2025)
- [VLLaVO: Mitigating Visual Gap through LLMs](https://mlsanity.com/paper/2401.03253/) (2024)
- [DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors](https://mlsanity.com/paper/2311.17098/) (2023)
- [DyRoNet: Dynamic Routing and Low-Rank Adapters for Autonomous Driving Streaming Perception](https://mlsanity.com/paper/2403.05050/) (2024)
- [PK-YOLO: Pretrained Knowledge Guided YOLO for Brain Tumor Detection in Multiplanar MRI Slices](https://mlsanity.com/paper/2410.21822/) (2024)
- [Gun Detection Using Combined Human Pose and Weapon Appearance](https://mlsanity.com/paper/2503.12215/) (2025)
- [Real Time American Sign Language Detection Using Yolo-v9](https://mlsanity.com/paper/2407.17950/) (2024)
- [Enhancing Adaptive Deep Networks for Image Classification via Uncertainty-aware Decision Fusion](https://mlsanity.com/paper/2408.13744/) (2024)
- [Multi-QuAD: Multi-Level Quality-Adaptive Dynamic Network for Reliable Multimodal Classification](https://mlsanity.com/paper/2412.14489/) (2024)
- [YOLO-ROC: A High-Precision and Ultra-Lightweight Model for Real-Time Road Damage Detection](https://mlsanity.com/paper/2507.23225/) (2025)
- [BlankSkip: Early-exit Object Detection onboard Nano-drones](https://mlsanity.com/paper/2603.28149/) (2026)
- [AnyDepth-DETR/-YOLO: Any-depth object detection with a single network](https://mlsanity.com/paper/2605.09407/) (2026)

## Abstract (arXiv)

Dynamic neural network is an emerging research topic in deep learning. With adaptive inference, dynamic models can achieve remarkable accuracy and computational efficiency. However, it is challenging to design a powerful dynamic detector, because of no suitable dynamic architecture and exiting criterion for object detection. To tackle these difficulties, we propose a dynamic framework for object detection, named DynamicDet. Firstly, we carefully design a dynamic architecture based on the nature of the object detection task. Then, we propose an adaptive router to analyze the multi-scale information and to decide the inference route automatically. We also present a novel optimization strategy with an exiting criterion based on the detection losses for our dynamic detectors. Last, we present a variable-speed inference strategy, which helps to realize a wide range of accuracy-speed trade-offs with only one dynamic detector. Extensive experiments conducted on the COCO benchmark demonstrate that the proposed DynamicDet achieves new state-of-the-art accuracy-speed trade-offs. For instance, with comparable accuracy, the inference speed of our dynamic detector Dy-YOLOv7-W6 surpasses YOLOv7-E6 by 12%, YOLOv7-D6 by 17%, and YOLOv7-E6E by 39%. The code is available at https://github.com/VDIGPKU/DynamicDet.