# POLO -- Point-based, multi-class animal detection

arXiv: https://arxiv.org/abs/2410.11741 · HTML: https://mlsanity.com/paper/2410.11741/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 19 references that are in the map.
- First posted on arXiv 15 Oct 2024.

## Builds on (most cited first, 8 of 8)

- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework](https://mlsanity.com/paper/2107.12746/) (2021)
- [Points as Queries: Weakly Semi-supervised Object Detection by Points](https://mlsanity.com/paper/2104.07434/) (2021)
- [CrowdNet: A Deep Convolutional Network for Dense Crowd Counting](https://mlsanity.com/paper/1608.06197/) (2016)
- [Detecting Mammals in UAV Images: Best Practices to address a substantially Imbalanced Dataset with Deep Learning](https://mlsanity.com/paper/1806.11368/) (2018)
- [Locating Objects Without Bounding Boxes](https://mlsanity.com/paper/1806.07564/) (2018)
- [Group R-CNN for Weakly Semi-supervised Object Detection with Points](https://mlsanity.com/paper/2205.05920/) (2022)
- [Point-Teaching: Weakly Semi-Supervised Object Detection with Point Annotations](https://mlsanity.com/paper/2206.00274/) (2022)

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

- [Weakly supervised framework for wildlife detection and counting in challenging Arctic environments: a case study on caribou (Rangifer tarandus)](https://mlsanity.com/paper/2601.18891/) (2026)
- [Overhead Wildlife Locator (OWL): Benchmarking Weakly Supervised Learning for Aerial Wildlife Surveys](https://mlsanity.com/paper/2606.13911/) (2026)
- [MMLA: Multi-Environment, Multi-Species, Low-Altitude Drone Dataset](https://mlsanity.com/paper/2504.07744/) (2025)
- [WildBox: A Dataset and Benchmark for Aerial Monocular 3D Detection of African Savanna Wildlife](https://mlsanity.com/paper/2606.21309/) (2026)
- [trACT: temporal revelation Airborne Camera Trap](https://mlsanity.com/paper/2610.09417/) (2026)

## Abstract (arXiv)

Automated wildlife surveys based on drone imagery and object detection technology are a powerful and increasingly popular tool in conservation biology. Most detectors require training images with annotated bounding boxes, which are tedious, expensive, and not always unambiguous to create. To reduce the annotation load associated with this practice, we develop POLO, a multi-class object detection model that can be trained entirely on point labels. POLO is based on simple, yet effective modifications to the YOLOv8 architecture, including alterations to the prediction process, training losses, and post-processing. We test POLO on drone recordings of waterfowl containing up to multiple thousands of individual birds in one image and compare it to a regular YOLOv8. Our experiments show that at the same annotation cost, POLO achieves improved accuracy in counting animals in aerial imagery.