Year: 2020
Type: article
Abstract: Metric learning is an important problem in machine learning. It aims to group similar observations together. Existing state-of-the-art metric learning approaches require class labels to induce a metric. Sometimes it is expensive or not possible to collect these labels. In this paper, we propose an unsupervised learning approach that learns a metric without making use of class labels. The lack of class labels is compensated by obtaining pseudo-labels of data using a graph-based clustering approach. The pseudo-labels are used to form triplets of examples, which guide the metric learning process. We propose a probabilistic loss function that minimizes the chances of each triplet violating an angular constraint. A weight function and an orthogonality constraint in the objective speed up convergence and avoid a model collapse. We also provide a stochastic formulation of our method to scale up to large-scale datasets. Our studies demonstrate the competitiveness of our approach against state-of-the-art methods.
Authors: Ujjal Kr Dutta, Mehrtash Harandi, Chellu Chandra Sekhar
Institutions: Monash University, Indian Institute of Technology Madras
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3080164465
