README.md

# GAnet

[Guided Attention Network for Object Detection and Counting on Drones](https://arxiv.org/abs/1909.11307v1).

This paper is accepted by ACM MM 2020.

## Introduction

Object detection and counting are related but challenging problems, especially for drone based scenes with small objects and cluttered background. In this paper, we propose a new Guided Attention network (GAnet) to deal with both object detection and counting tasks based on the feature pyramid. Different from the previous methods relying on unsupervised attention modules, we fuse different scales of feature maps by using the proposed weakly-supervised Background Attention (BA) between the background and objects for more semantic feature representation. Then, the Foreground Attention (FA) module is developed to consider both global and local appearance of the object to facilitate accurate localization. Moreover, the new data argumentation strategy is designed to train a robust model in the drone based scenes with various illumination conditions. Extensive experiments on three challenging benchmarks (\ie, UAVDT, CARPK and PUCPR+) show the state-of-the-art detection and counting performance of the proposed method compared with existing methods.

![GAnet](Demo/framework.jpg)

## Citation
If you find this code useful for your research, please cite
```
@inproceedings{Cai2020GAnet,
  title={Guided Attention Network for Object Detection and Counting on Drones},
  author={Yuanqiang, Cai and Dawei, Du and Libo, Zhang and Longyin, Wen and Weiqiang, Wang and Yanjun, Wu and Siwei, Lyu},
  booktitle={2020 ACM Multimedia Conference on Multimedia Conference},
  year={2020},
  organization={ACM}
}
```