HIER: Metric Learning Beyond Class Labels via Hierarchical Regularization

by   Sungyeon Kim, et al.

Supervision for metric learning has long been given in the form of equivalence between human-labeled classes. Although this type of supervision has been a basis of metric learning for decades, we argue that it hinders further advances of the field. In this regard, we propose a new regularization method, dubbed HIER, to discover the latent semantic hierarchy of training data, and to deploy the hierarchy to provide richer and more fine-grained supervision than inter-class separability induced by common metric learning losses. HIER achieved this goal with no annotation for the semantic hierarchy but by learning hierarchical proxies in hyperbolic spaces. The hierarchical proxies are learnable parameters, and each of them is trained to serve as an ancestor of a group of data or other proxies to approximate the semantic hierarchy among them. HIER deals with the proxies along with data in hyperbolic space since geometric properties of the space are well-suited to represent their hierarchical structure. The efficacy of HIER was evaluated on four standard benchmarks, where it consistently improved performance of conventional methods when integrated with them, and consequently achieved the best records, surpassing even the existing hyperbolic metric learning technique, in almost all settings.


page 7

page 8

page 12


Hierarchical Metric Learning for Fine Grained Image Classification

This paper deals with the problem of fine-grained image classification a...

Inspecting class hierarchies in classification-based metric learning models

Most classification models treat all misclassifications equally. However...

Hierarchical Annotation of Images with Two-Alternative-Forced-Choice Metric Learning

Many tasks such as retrieval and recommendations can significantly benef...

Hierarchical Proxy-based Loss for Deep Metric Learning

Proxy-based metric learning losses are superior to pair-based losses due...

A Metric Learning Reality Check

Deep metric learning papers from the past four years have consistently c...

Metric-Guided Prototype Learning

Not all errors are created equal. This is especially true for many key m...

Please sign up or login with your details

Forgot password? Click here to reset