# Locating Objects Without Bounding Boxes

arXiv: https://arxiv.org/abs/1806.07564 · HTML: https://mlsanity.com/paper/1806.07564/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2018.

## Built on by (most cited first, 25 of 25)

- [An End-to-End Transformer Model for Crowd Localization](https://mlsanity.com/paper/2202.13065/) (2022)
- [Focal Inverse Distance Transform Maps for Crowd Localization](https://mlsanity.com/paper/2102.07925/) (2021)
- [Point-to-Box Network for Accurate Object Detection via Single Point Supervision](https://mlsanity.com/paper/2207.06827/) (2022)
- [Diffeomorphic Counterfactuals with Generative Models](https://mlsanity.com/paper/2206.05075/) (2022)
- [Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance](https://mlsanity.com/paper/2405.10589/) (2024)
- [Object Localization under Single Coarse Point Supervision](https://mlsanity.com/paper/2203.09338/) (2022)
- [DeepMesh: Mesh-based Cardiac Motion Tracking using Deep Learning](https://mlsanity.com/paper/2309.14306/) (2023)
- [Mesh-based 3D Motion Tracking in Cardiac MRI using Deep Learning](https://mlsanity.com/paper/2209.02004/) (2022)
- [Consistency-Aware Anchor Pyramid Network for Crowd Localization](https://mlsanity.com/paper/2212.04067/) (2022)
- [Learning Remote Sensing Object Detection with Single Point Supervision](https://mlsanity.com/paper/2305.14141/) (2023)
- [VMambaCC: A Visual State Space Model for Crowd Counting](https://mlsanity.com/paper/2405.03978/) (2024)
- [POLO -- Point-based, multi-class animal detection](https://mlsanity.com/paper/2410.11741/) (2024)
- [Rotor Localization and Phase Mapping of Cardiac Excitation Waves using Deep Neural Networks](https://mlsanity.com/paper/2109.10472/) (2021)
- [Spatial Feature Mapping for 6DoF Object Pose Estimation](https://mlsanity.com/paper/2206.01831/) (2022)
- [Dense Center-Direction Regression for Object Counting and Localization with Point Supervision](https://mlsanity.com/paper/2408.14457/) (2024)
- [Machine Learning for the Digital Typhoon Dataset: Extensions to Multiple Basins and New Developments in Representations and Tasks](https://mlsanity.com/paper/2411.16421/) (2024)
- [ASTRA: A Scene-aware TRAnsformer-based model for trajectory prediction](https://mlsanity.com/paper/2501.09878/) (2025)
- [Bag-of-Vectors Autoencoders for Unsupervised Conditional Text Generation](https://mlsanity.com/paper/2110.07002/) (2021)
- [Centroid-UNet: Detecting Centroids in Aerial Images](https://mlsanity.com/paper/2112.06530/) (2021)
- [CPR++: Object Localization via Single Coarse Point Supervision](https://mlsanity.com/paper/2401.17203/) (2024)
- [P2Object: Single Point Supervised Object Detection and Instance Segmentation](https://mlsanity.com/paper/2504.07813/) (2025)
- [BoundaryNet: An Attentive Deep Network with Fast Marching Distance Maps for Semi-automatic Layout Annotation](https://mlsanity.com/paper/2108.09433/) (2021)
- [P2P-Loc: Point to Point Tiny Person Localization](https://mlsanity.com/paper/2112.15344/) (2021)
- [A Computer Vision Enabled damage detection model with improved YOLOv5 based on Transformer Prediction Head](https://mlsanity.com/paper/2303.04275/) (2023)
- [EHNet: An Efficient Hybrid Network for Crowd Counting and Localization](https://mlsanity.com/paper/2503.12061/) (2025)

## Abstract (arXiv)

Recent advances in convolutional neural networks (CNN) have achieved remarkable results in locating objects in images. In these networks, the training procedure usually requires providing bounding boxes or the maximum number of expected objects. In this paper, we address the task of estimating object locations without annotated bounding boxes which are typically hand-drawn and time consuming to label. We propose a loss function that can be used in any fully convolutional network (FCN) to estimate object locations. This loss function is a modification of the average Hausdorff distance between two unordered sets of points. The proposed method has no notion of bounding boxes, region proposals, or sliding windows. We evaluate our method with three datasets designed to locate people's heads, pupil centers and plant centers. We outperform state-of-the-art generic object detectors and methods fine-tuned for pupil tracking.