# LOOC: Localize Overlapping Objects with Count Supervision

arXiv: https://arxiv.org/abs/2007.01837 · HTML: https://mlsanity.com/paper/2007.01837/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2020.

## Built on by (most cited first, 4 of 4)

- [Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data](https://mlsanity.com/paper/2103.16607/) (2021)
- [A Survey of Self-Supervised and Few-Shot Object Detection](https://mlsanity.com/paper/2110.14711/) (2021)
- [A Deep Learning Localization Method for Measuring Abdominal Muscle Dimensions in Ultrasound Images](https://mlsanity.com/paper/2109.14919/) (2021)
- [Detecting Cattle and Elk in the Wild from Space](https://mlsanity.com/paper/2106.15448/) (2021)

## Abstract (arXiv)

Acquiring count annotations generally requires less human effort than point-level and bounding box annotations. Thus, we propose the novel problem setup of localizing objects in dense scenes under this weaker supervision. We propose LOOC, a method to Localize Overlapping Objects with Count supervision. We train LOOC by alternating between two stages. In the first stage, LOOC learns to generate pseudo point-level annotations in a semi-supervised manner. In the second stage, LOOC uses a fully-supervised localization method that trains on these pseudo labels. The localization method is used to progressively improve the quality of the pseudo labels. We conducted experiments on popular counting datasets. For localization, LOOC achieves a strong new baseline in the novel problem setup where only count supervision is available. For counting, LOOC outperforms current state-of-the-art methods that only use count as their supervision. Code is available at: https://github.com/ElementAI/looc.