# Weakly-supervised multi-class object localization using only object counts as labels

arXiv: https://arxiv.org/abs/2102.11743 · HTML: https://mlsanity.com/paper/2102.11743/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 25 references that are in the map.
- First posted on arXiv 23 Feb 2021.

## Builds on (most cited first, 9 of 9)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Count-ception: Counting by Fully Convolutional Redundant Counting](https://mlsanity.com/paper/1703.08710/) (2017)
- [A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation](https://mlsanity.com/paper/1707.01202/) (2017)
- [Multi-scale Convolutional Neural Networks for Crowd Counting](https://mlsanity.com/paper/1702.02359/) (2017)
- [People, Penguins and Petri Dishes: Adapting Object Counting Models To New Visual Domains And Object Types Without Forgetting](https://mlsanity.com/paper/1711.05586/) (2017)
- [Image Crowd Counting Using Convolutional Neural Network and Markov Random Field](https://mlsanity.com/paper/1706.03686/) (2017)
- [Counting Cells in Time-Lapse Microscopy using Deep Neural Networks](https://mlsanity.com/paper/1801.10443/) (2018)

## Abstract (arXiv)

We demonstrate the use of an extensive deep neural network to localize instances of objects in images. The EDNN is naturally able to accurately perform multi-class counting using only ground truth count values as labels. Without providing any conceptual information, object annotations, or pixel segmentation information, the neural network is able to formulate its own conceptual representation of the items in the image. Using images labelled with only the counts of the objects present,the structure of the extensive deep neural network can be exploited to perform localization of the objects within the visual field. We demonstrate that a trained EDNN can be used to count objects in images much larger than those on which it was trained. In order to demonstrate our technique, we introduce seven new data sets: five progressively harder MNIST digit-counting data sets, and two datasets of 3d-rendered rubber ducks in various situations. On most of these datasets, the EDNN achieves greater than 99% test set accuracy in counting objects.