# Dense Center-Direction Regression for Object Counting and Localization with Point Supervision

arXiv: https://arxiv.org/abs/2408.14457 · HTML: https://mlsanity.com/paper/2408.14457/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 41 references that are in the map.
- First posted on arXiv 26 Aug 2024.

## Builds on (most cited first, 24 of 24)

- [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)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [Weakly Supervised Deep Detection Networks](https://mlsanity.com/paper/1511.02853/) (2015)
- [Drone-based Object Counting by Spatially Regularized Regional Proposal Network](https://mlsanity.com/paper/1707.05972/) (2017)
- [Distribution Matching for Crowd Counting](https://mlsanity.com/paper/2009.13077/) (2020)
- [PCL: Proposal Cluster Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/1807.03342/) (2018)
- [Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth](https://mlsanity.com/paper/1906.11109/) (2019)
- [C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/1904.05647/) (2019)
- [Precise Detection in Densely Packed Scenes](https://mlsanity.com/paper/1904.00853/) (2019)
- [Object Counting and Instance Segmentation with Image-level Supervision](https://mlsanity.com/paper/1903.02494/) (2019)
- [Towards Using Count-level Weak Supervision for Crowd Counting](https://mlsanity.com/paper/2003.00164/) (2020)
- [Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing](https://mlsanity.com/paper/2103.04570/) (2021)
- [Locating Objects Without Bounding Boxes](https://mlsanity.com/paper/1806.07564/) (2018)
- [Guided Attention Network for Object Detection and Counting on Drones](https://mlsanity.com/paper/1909.11307/) (2019)
- [Coarse- and Fine-grained Attention Network with Background-aware Loss for Crowd Density Map Estimation](https://mlsanity.com/paper/2011.03721/) (2020)
- [CrowdFormer: Weakly-supervised Crowd counting with Improved Generalizability](https://mlsanity.com/paper/2203.03768/) (2022)
- [CrowdMLP: Weakly-Supervised Crowd Counting via Multi-Granularity MLP](https://mlsanity.com/paper/2203.08219/) (2022)
- [Counting and Locating High-Density Objects Using Convolutional Neural Network](https://mlsanity.com/paper/2102.04366/) (2021)

## Built on by (most cited first, 3 of 3)

- [ClickTrack: Towards Real-time Interactive Single Object Tracking](https://mlsanity.com/paper/2411.13183/) (2024)
- [Text-guided Zero-Shot Object Localization](https://mlsanity.com/paper/2411.11357/) (2024)
- [Vision-Based 6-DoF Grasp Pose Estimation for Robot Cloth Unfolding](https://mlsanity.com/paper/2609.31452/) (2026)

## Abstract (arXiv)

Object counting and localization problems are commonly addressed with point supervised learning, which allows the use of less labor-intensive point annotations. However, learning based on point annotations poses challenges due to the high imbalance between the sets of annotated and unannotated pixels, which is often treated with Gaussian smoothing of point annotations and focal loss. However, these approaches still focus on the pixels in the immediate vicinity of the point annotations and exploit the rest of the data only indirectly. In this work, we propose a novel approach termed CeDiRNet for point-supervised learning that uses a dense regression of directions pointing towards the nearest object centers, i.e. center-directions. This provides greater support for each center point arising from many surrounding pixels pointing towards the object center. We propose a formulation of center-directions that allows the problem to be split into the domain-specific dense regression of center-directions and the final localization task based on a small, lightweight, and domain-agnostic localization network that can be trained with synthetic data completely independent of the target domain. We demonstrate the performance of the proposed method on six different datasets for object counting and localization, and show that it outperforms the existing state-of-the-art methods. The code is accessible on GitHub at https://github.com/vicoslab/CeDiRNet.git.