# Scale Optimization Using Evolutionary Reinforcement Learning for Object Detection on Drone Imagery

arXiv: https://arxiv.org/abs/2312.15219 · HTML: https://mlsanity.com/paper/2312.15219/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 50 references that are in the map.
- First posted on arXiv 23 Dec 2023.

## Builds on (most cited first, 21 of 21)

- [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)
- [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)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [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)
- [Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection](https://mlsanity.com/paper/2006.04388/) (2020)
- [Detection and Tracking Meet Drones Challenge](https://mlsanity.com/paper/2001.06303/) (2020)
- [Scaled-YOLOv4: Scaling Cross Stage Partial Network](https://mlsanity.com/paper/2011.08036/) (2020)
- [The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking](https://mlsanity.com/paper/1804.00518/) (2018)
- [Acquisition of Localization Confidence for Accurate Object Detection](https://mlsanity.com/paper/1807.11590/) (2018)
- [Clustered Object Detection in Aerial Images](https://mlsanity.com/paper/1904.08008/) (2019)
- [Perceptual Generative Adversarial Networks for Small Object Detection](https://mlsanity.com/paper/1706.05274/) (2017)
- [Density Map Guided Object Detection in Aerial Images](https://mlsanity.com/paper/2004.05520/) (2020)
- [UFPMP-Det: Toward Accurate and Efficient Object Detection on Drone Imagery](https://mlsanity.com/paper/2112.10415/) (2021)
- [HRDNet: High-resolution Detection Network for Small Objects](https://mlsanity.com/paper/2006.07607/) (2020)
- [Actor-Critic Instance Segmentation](https://mlsanity.com/paper/1904.05126/) (2019)
- [Spatial-context-aware deep neural network for multi-class image classification](https://mlsanity.com/paper/2111.12296/) (2021)

## Built on by (most cited first, 5 of 5)

- [Language-guided Learning for Object Detection Tackling Multiple Variations in Aerial Images](https://mlsanity.com/paper/2505.23193/) (2025)
- [YOLO-Drone: An Efficient Object Detection Approach Using the GhostHead Network for Drone Images](https://mlsanity.com/paper/2511.10905/) (2025)
- [A text-guided vision model for enhanced recognition of small instances](https://mlsanity.com/paper/2602.19503/) (2026)
- [GCA-SUNet: A Gated Context-Aware Swin-UNet for Exemplar-Free Counting](https://mlsanity.com/paper/2409.12249/) (2024)
- [Variable-Granularity Tokenization for High-Resolution Object Detection](https://mlsanity.com/paper/2608.28706/) (2026)

## Abstract (arXiv)

Object detection in aerial imagery presents a significant challenge due to large scale variations among objects. This paper proposes an evolutionary reinforcement learning agent, integrated within a coarse-to-fine object detection framework, to optimize the scale for more effective detection of objects in such images. Specifically, a set of patches potentially containing objects are first generated. A set of rewards measuring the localization accuracy, the accuracy of predicted labels, and the scale consistency among nearby patches are designed in the agent to guide the scale optimization. The proposed scale-consistency reward ensures similar scales for neighboring objects of the same category. Furthermore, a spatial-semantic attention mechanism is designed to exploit the spatial semantic relations between patches. The agent employs the proximal policy optimization strategy in conjunction with the evolutionary strategy, effectively utilizing both the current patch status and historical experience embedded in the agent. The proposed model is compared with state-of-the-art methods on two benchmark datasets for object detection on drone imagery. It significantly outperforms all the compared methods.