# Unsupervised Image Matching and Object Discovery as Optimization

## TL;DR

This paper reformulates unsupervised image matching and object discovery as a proper optimization problem, demonstrating its effectiveness through experiments on multiple benchmarks, thus advancing unsupervised learning in computer vision.

## Contribution

It introduces a novel optimization-based formulation for unsupervised object discovery and matching, improving upon previous heuristic methods.

## Key findings

- Effective on multiple benchmarks
- Outperforms previous unsupervised methods
- Validates the optimization approach

## Abstract

Learning with complete or partial supervision is powerful but relies on ever-growing human annotation efforts. As a way to mitigate this serious problem, as well as to serve specific applications, unsupervised learning has emerged as an important field of research. In computer vision, unsupervised learning comes in various guises. We focus here on the unsupervised discovery and matching of object categories among images in a collection, following the work of Cho et al. 2015. We show that the original approach can be reformulated and solved as a proper optimization problem. Experiments on several benchmarks establish the merit of our approach.