Semi-Supervised Metric Learning: A Deep Resurrection

05/10/2021
by   Ujjal Kr Dutta, et al.
0

Distance Metric Learning (DML) seeks to learn a discriminative embedding where similar examples are closer, and dissimilar examples are apart. In this paper, we address the problem of Semi-Supervised DML (SSDML) that tries to learn a metric using a few labeled examples, and abundantly available unlabeled examples. SSDML is important because it is infeasible to manually annotate all the examples present in a large dataset. Surprisingly, with the exception of a few classical approaches that learn a linear Mahalanobis metric, SSDML has not been studied in the recent years, and lacks approaches in the deep SSDML scenario. In this paper, we address this challenging problem, and revamp SSDML with respect to deep learning. In particular, we propose a stochastic, graph-based approach that first propagates the affinities between the pairs of examples from labeled data, to that of the unlabeled pairs. The propagated affinities are used to mine triplet based constraints for metric learning. We impose orthogonality constraint on the metric parameters, as it leads to a better performance by avoiding a model collapse.

READ FULL TEXT

page 2

page 6

research
02/27/2020

Affinity guided Geometric Semi-Supervised Metric Learning

In this paper, we address the semi-supervised metric learning problem, w...
research
04/29/2020

Metric learning by Similarity Network for Deep Semi-Supervised Learning

Deep semi-supervised learning has been widely implemented in the real-wo...
research
02/23/2022

Deep Metric Learning-Based Semi-Supervised Regression With Alternate Learning

This paper introduces a novel deep metric learning-based semi-supervised...
research
04/28/2022

Mixup-based Deep Metric Learning Approaches for Incomplete Supervision

Deep learning architectures have achieved promising results in different...
research
05/01/2011

SERAPH: Semi-supervised Metric Learning Paradigm with Hyper Sparsity

We propose a general information-theoretic approach called Seraph (SEmi-...
research
02/21/2020

An end-to-end approach for the verification problem: learning the right distance

In this contribution, we augment the metric learning setting by introduc...
research
04/07/2021

Deep Semi-supervised Metric Learning with Dual Alignment for Cervical Cancer Cell Detection

With availability of huge amounts of labeled data, deep learning has ach...

Please sign up or login with your details

Forgot password? Click here to reset