Deep Metric Learning Meets Deep Clustering: An Novel Unsupervised Approach For Feature Embedding

Abstract

Unsupervised Deep Distance Metric Learning (UDML) aims to learn sample similarities in the embedding space from an unlabeled dataset. Traditional UDML methods usually use the triplet loss or pairwise loss which requires the mining of positive and negative samples w.r.t. anchor data points. This is, however, challenging in an unsupervised setting as the label information is not available. In this paper, we propose a new UDML method that overcomes that challenge. In particular, we propose to use a deep clustering loss to learn centroids, i.e., pseudo labels, that represent semantic classes. During learning, these centroids are also used to reconstruct the input samples. It hence ensures the representativeness of centroids - each centroid represents visually similar samples. Therefore, the centroids give information about positive (visually similar) and negative (visually dissimilar) samples. Based on pseudo labels, we propose a novel unsupervised metric loss which enforces the positive c

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keynguyen2020deep

Related papers

• Piecewise-linear Manifolds For Deep Metric Learning (2024)0.00
• Guided Deep Metric Learning (2022)6.77
• Deep Relational Metric Learning (2021)12.17
• Directional Statistics-based Deep Metric Learning For Image Classification And Retrieval (2018)13.05
• Deep Metric Learning Via Facility Location (2016)17.16
• Semi-supervised Deep Learning By Metric Embedding (2016)0.00
• The Group Loss For Deep Metric Learning (2019)11.39
• Deep Metric Learning Assisted By Intra-variance In A Semi-supervised View Of Learning (2023)5.24