# Deep Unsupervised Similarity Learning using Partially Ordered Sets

## TL;DR

This paper introduces a novel unsupervised deep learning method that uses local partial orders and surrogate classes to learn visual similarities, overcoming the unreliability of pairwise relations.

## Contribution

It proposes a unified model that combines similarity learning and grouping via partial orders, enabling self-supervised training without labeled data.

## Key findings

- Achieves competitive results in pose estimation
- Performs well in object classification tasks
- Effectively handles unreliable pairwise relations

## Abstract

Unsupervised learning of visual similarities is of paramount importance to computer vision, particularly due to lacking training data for fine-grained similarities. Deep learning of similarities is often based on relationships between pairs or triplets of samples. Many of these relations are unreliable and mutually contradicting, implying inconsistencies when trained without supervision information that relates different tuples or triplets to each other. To overcome this problem, we use local estimates of reliable (dis-)similarities to initially group samples into compact surrogate classes and use local partial orders of samples to classes to link classes to each other. Similarity learning is then formulated as a partial ordering task with soft correspondences of all samples to classes. Adopting a strategy of self-supervision, a CNN is trained to optimally represent samples in a mutually consistent manner while updating the classes. The similarity learning and grouping procedure are integrated in a single model and optimized jointly. The proposed unsupervised approach shows competitive performance on detailed pose estimation and object classification.