Exponential triplet loss

Urtans, Evalds; Nitkitenko, Agris; Vecins, Valters

doi:10.1145/3388142.3388163

Cited by 5 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[ 21 ] introduced the ranked list loss to deal with sampling issues, and used data from non-trivial data points as well. Alternatives of the triplet loss, such as exponential triplet loss [ 22 ] and lossless triplet loss [ 23 ], have also been shown to be promising alternatives. It is also worth mentioning that a recent study showed that classical methods show similar performances to state-of-the-art loss functions [ 24 ].…”

Section: Introductionmentioning

confidence: 99%

Deep Metric Learning Using Negative Sampling Probability Annealing

Kertész

2022

Sensors

View full text Add to dashboard Cite

Multiple studies have concluded that the selection of input samples is key for deep metric learning. For triplet networks, the selection of the anchor, positive, and negative pairs is referred to as triplet mining. The selection of the negatives is considered the be the most complicated task, due to a large number of possibilities. The goal is to select a negative that results in a positive triplet loss; however, there are multiple approaches for this—semi-hard negative mining or hardest mining are well-known in addition to random selection. Since its introduction, semi-hard mining was proven to outperform other negative mining techniques; however, in recent years, the selection of the so-called hardest negative has shown promising results in different experiments. This paper introduces a novel negative sampling solution based on dynamic policy switching, referred to as negative sampling probability annealing, which aims to exploit the positives of all approaches. Results are validated on an experimental synthetic dataset using cluster-analysis methods; finally, the discriminative abilities of trained models are measured on real-life data.

show abstract