Deep learning architectures have achieved promising results in different areas (e.g., medicine, agriculture, and security). However, using those powerful techniques in many real applications becomes challenging due to the large labeled collections required during training. Several works have pursued solutions to overcome it by proposing strategies that can learn more for less, e.g., weakly and semi-supervised learning approaches. As these approaches do not usually address memorization and sensitivity to adversarial examples, this paper presents three deep metric learning approaches combined with Mixup for incomplete-supervision scenarios. We show that some state-of-the-art approaches in metric learning might not work well in such scenarios. Moreover, the proposed approaches outperform most of them in different datasets.

翻译：深层学习结构在不同领域(如医学、农业和安全)取得了可喜的成果。然而,由于培训期间需要大量有标签的收集,因此在许多实际应用中使用这些强有力的技术变得具有挑战性。一些工作力求通过提出可以少学、少学、少学和半监督学习方法等战略来克服这一困难。由于这些方法通常不处理记忆和对对抗实例的敏感性问题,本文件介绍了三种深层次的、与不完全监督情景混合混合的衡量学习方法。我们表明,在这类情况下,一些最先进的计量学习方法可能效果不佳。此外,拟议的方法在不同的数据集中比大多数方法都好。