A Probabilistic approach for Learning Embeddings without Supervision

TL;DR

This paper introduces an unsupervised probabilistic method for learning data embeddings by leveraging graph-based clustering and Riemannian geometry, eliminating the need for labeled data while achieving competitive results.

Contribution

It presents a novel unsupervised embedding learning approach that uses probabilistic triplet constraints and Riemannian optimization, advancing beyond supervised methods.

Findings

Achieves competitive performance with state-of-the-art supervised methods.

Effectively learns discriminative embeddings without class labels.

Utilizes a graph-based clustering to generate pseudo-labels.

Abstract

For challenging machine learning problems such as zero-shot learning and fine-grained categorization, embedding learning is the machinery of choice because of its ability to learn generic notions of similarity, as opposed to class-specific concepts in standard classification models. Embedding learning aims at learning discriminative representations of data such that similar examples are pulled closer, while pushing away dissimilar ones. Despite their exemplary performances, supervised embedding learning approaches require huge number of annotations for training. This restricts their applicability for large datasets in new applications where obtaining labels require extensive manual efforts and domain knowledge. In this paper, we propose to learn an embedding in a completely unsupervised manner without using any class labels. Using a graph-based clustering approach to obtain pseudo-labels, we form triplet-based constraints following a metric learning paradigm. Our novel embedding learning approach uses a probabilistic notion, that intuitively minimizes the chances of each triplet violating a geometric constraint. Due to nature of the search space, we learn the parameters of our approach using Riemannian geometry. Our proposed approach performs competitive to state-of-the-art approaches.