# StampNet: unsupervised multi-class object discovery

## TL;DR

StampNet is an unsupervised neural network that simultaneously localizes and categorizes objects in images, effectively discovering recurring patterns without supervision, demonstrated on shape datasets and pedestrian localization.

## Contribution

It introduces StampNet, a novel autoencoder with a discrete latent space for unsupervised multi-object localization and categorization in images.

## Key findings

- Successfully localizes and clusters overlapping shapes.
- Effectively categorizes objects in MNIST digits.
- Applies to pedestrian localization in depth-maps.

## Abstract

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.