It Takes Two to Tango: Mixup for Deep Metric Learning

by   Shashanka Venkataramanan, et al.

Metric learning involves learning a discriminative representation such that embeddings of similar classes are encouraged to be close, while embeddings of dissimilar classes are pushed far apart. State-of-the-art methods focus mostly on sophisticated loss functions or mining strategies. On the one hand, metric learning losses consider two or more examples at a time. On the other hand, modern data augmentation methods for classification consider two or more examples at a time. The combination of the two ideas is under-studied. In this work, we aim to bridge this gap and improve representations using mixup, which is a powerful data augmentation approach interpolating two or more examples and corresponding target labels at a time. This task is challenging because, unlike classification, the loss functions used in metric learning are not additive over examples, so the idea of interpolating target labels is not straightforward. To the best of our knowledge, we are the first to investigate mixing examples and target labels for deep metric learning. We develop a generalized formulation that encompasses existing metric learning loss functions and modify it to accommodate for mixup, introducing Metric Mix, or Metrix. We show that mixing inputs, intermediate representations or embeddings along with target labels significantly improves representations and outperforms state-of-the-art metric learning methods on four benchmark datasets.


page 1

page 2

page 3

page 4


DIABLO: Dictionary-based Attention Block for Deep Metric Learning

Recent breakthroughs in representation learning of unseen classes and ex...

Unsupervised Deep Metric Learning via Orthogonality based Probabilistic Loss

Metric learning is an important problem in machine learning. It aims to ...

Mean Field Theory in Deep Metric Learning

In this paper, we explore the application of mean field theory, a techni...

Do Different Deep Metric Learning Losses Lead to Similar Learned Features?

Recent studies have shown that many deep metric learning loss functions ...

Supervised Metric Learning for Music Structure Feature

Music structure analysis (MSA) methods traditionally search for musicall...

Exploring Adversarial Robustness of Deep Metric Learning

Deep Metric Learning (DML), a widely-used technique, involves learning a...

Asymmetric metric learning for knowledge transfer

Knowledge transfer from large teacher models to smaller student models h...

Please sign up or login with your details

Forgot password? Click here to reset