# Dynamic Scale Training for Object Detection

arXiv: https://arxiv.org/abs/2004.12432 · HTML: https://mlsanity.com/paper/2004.12432/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Apr 2020.

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

- [Poly Kernel Inception Network for Remote Sensing Detection](https://mlsanity.com/paper/2403.06258/) (2024)
- [MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection](https://mlsanity.com/paper/2102.08884/) (2021)
- [Scale-aware Automatic Augmentation for Object Detection](https://mlsanity.com/paper/2103.17220/) (2021)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [Remote Sensing Object Detection Meets Deep Learning: A Meta-review of Challenges and Advances](https://mlsanity.com/paper/2309.06751/) (2023)
- [ESOD: Efficient Small Object Detection on High-Resolution Images](https://mlsanity.com/paper/2407.16424/) (2024)
- [A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance](https://mlsanity.com/paper/2207.12926/) (2022)
- [VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges](https://mlsanity.com/paper/2103.03768/) (2021)
- [Learning with Free Object Segments for Long-Tailed Instance Segmentation](https://mlsanity.com/paper/2202.11124/) (2022)
- [Improving Crowded Object Detection via Copy-Paste](https://mlsanity.com/paper/2211.12110/) (2022)
- [Rethinking Training from Scratch for Object Detection](https://mlsanity.com/paper/2106.03112/) (2021)
- [Small Object Tracking in LiDAR Point Cloud: Learning the Target-awareness Prototype and Fine-grained Search Region](https://mlsanity.com/paper/2401.13285/) (2024)
- [Data-Efficient Challenges in Visual Inductive Priors: A Retrospective](https://mlsanity.com/paper/2506.08612/) (2025)
- [PKINet-v2: Towards Powerful and Efficient Poly-Kernel Remote Sensing Object Detection](https://mlsanity.com/paper/2603.16341/) (2026)
- [Can Multimodal Large Language Models Truly Understand Small Objects?](https://mlsanity.com/paper/2604.22884/) (2026)

## Abstract (arXiv)

We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection. Previous strategies like image pyramid, multi-scale training, and their variants are aiming at preparing scale-invariant data for model optimization. However, the preparation procedure is unaware of the following optimization process that restricts their capability in handling the scale variation. Instead, in our paradigm, we use feedback information from the optimization process to dynamically guide the data preparation. The proposed method is surprisingly simple yet obtains significant gains (2%+ Average Precision on MS COCO dataset), outperforming previous methods. Experimental results demonstrate the efficacy of our proposed DST method towards scale variation handling. It could also generalize to various backbones, benchmarks, and other challenging downstream tasks like instance segmentation. It does not introduce inference overhead and could serve as a free lunch for general detection configurations. Besides, it also facilitates efficient training due to fast convergence. Code and models are available at github.com/yukang2017/Stitcher.