Pith. sign in

REVIEW 2 cited by

It Takes Two to Tango: Mixup for Deep Metric Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2106.04990 v2 pith:XVBEC43Z submitted 2021-06-09 cs.LG cs.CV

classification cs.LGcs.CV
keywords metriclearningexampleslabelsrepresentationstargetclassesdeep
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Metric Learning with Progressive Self-Distillation for Audio-Visual Embedding Learning

    cs.SD 2025-01 conditional novelty 4.0 of 10

    A self-distillation training scheme for audio-visual embeddings progressively replaces labeled triplets with model-generated soft alignments, improving cross-modal retrieval MAP by roughly 2 percent on AVE and VEGAS.

  2. Three Things to Know about Deep Metric Learning

    cs.CV 2024-12 conditional novelty 4.0 of 10

    RS@k loss, similarity mixup, and strong pre-trained initializations together raise deep metric learning benchmarks close to saturation.

Pith tools