Log In Sign Up

Fast Metric Learning For Deep Neural Networks

by   Henry Gouk, et al.

Similarity metrics are a core component of many information retrieval and machine learning systems. In this work we propose a method capable of learning a similarity metric from data equipped with a binary relation. By considering only the similarity constraints, and initially ignoring the features, we are able to learn target vectors for each instance using one of several appropriately designed loss functions. A regression model can then be constructed that maps novel feature vectors to the same target vector space, resulting in a feature extractor that computes vectors for which a predefined metric is a meaningful measure of similarity. We present results on both multiclass and multi-label classification datasets that demonstrate considerably faster convergence, as well as higher accuracy on the majority of the intrinsic evaluation tasks and all extrinsic evaluation tasks.


page 1

page 2

page 3

page 4


Positive semidefinite support vector regression metric learning

Most existing metric learning methods focus on learning a similarity or ...

Similarity Learning for High-Dimensional Sparse Data

A good measure of similarity between data points is crucial to many task...

Hierarchical Relationship Alignment Metric Learning

Most existing metric learning methods focus on learning a similarity or ...

A Hybrid Method for Distance Metric Learning

We consider the problem of learning a measure of distance among vectors ...

Metric Learning vs Classification for Disentangled Music Representation Learning

Deep representation learning offers a powerful paradigm for mapping inpu...

Patent Analytics Based on Feature Vector Space Model: A Case of IoT

The number of approved patents worldwide increases rapidly each year, wh...

Merging datasets through deep learning

Merging datasets is a key operation for data analytics. A frequent requi...