# StampNet: unsupervised multi-class object discovery

arXiv: https://arxiv.org/abs/1902.02693 · HTML: https://mlsanity.com/paper/1902.02693/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2019.

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

- [MarioNette: Self-Supervised Sprite Learning](https://mlsanity.com/paper/2104.14553/) (2021)
- [Unsupervised Object Discovery: A Comprehensive Survey and Unified Taxonomy](https://mlsanity.com/paper/2411.00868/) (2024)
- [Description Generation using Variational Auto-Encoders for precursor microRNA](https://mlsanity.com/paper/2311.17970/) (2023)
- [Deep Sprite-based Image Models: An Analysis](https://mlsanity.com/paper/2604.19480/) (2026)

## Abstract (arXiv)

Unsupervised object discovery in images involves uncovering recurring patterns that define objects and discriminates them against the background. This is more challenging than image clustering as the size and the location of the objects are not known: this adds additional degrees of freedom and increases the problem complexity. In this work, we propose StampNet, a novel autoencoding neural network that localizes shapes (objects) over a simple background in images and categorizes them simultaneously. StampNet consists of a discrete latent space that is used to categorize objects and to determine the location of the objects. The object categories are formed during the training, resulting in the discovery of a fixed set of objects. We present a set of experiments that demonstrate that StampNet is able to localize and cluster multiple overlapping shapes with varying complexity including the digits from the MNIST dataset. We also present an application of StampNet in the localization of pedestrians in overhead depth-maps.