It Takes Two to Tango: Mixup for Deep Metric Learning - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

It Takes Two to Tango: Mixup for Deep Metric Learning

Abstract

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 both 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 also introduce a new metric - utilization to demonstrate that by mixing examples during training, we are exploring areas of the embedding space beyond the training classes, thereby improving representations. To validate the effect of improved representations, we show that mixing inputs, intermediate representations or embeddings along with target labels significantly outperforms state-of-the-art metric learning methods on four benchmark deep metric learning datasets.
Fichier principal
Vignette du fichier
Metrix_ICLR22.pdf (30.38 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03577949 , version 1 (16-02-2022)

Identifiers

  • HAL Id : hal-03577949 , version 1

Cite

Shashanka Venkataramanan, Bill Psomas, Ewa Kijak, Laurent Amsaleg, Konstantinos Karantzalos, et al.. It Takes Two to Tango: Mixup for Deep Metric Learning. ICLR 2022 - 10th International Conference on Learning Representations, Apr 2022, Virtual, France. pp.1-21. ⟨hal-03577949⟩
92 View
55 Download

Share

Gmail Facebook X LinkedIn More