arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.14693cs.CVcs.LG
收藏

用于深度度量学习的基于自适应加性分类的损失

Adaptive additive classification-based loss for deep metric learning

Amazon(亚马逊)

Istvan Fehervari, Ives Macedo

摘要:

最近的工作表明,深度度量学习算法可以受益于来自另一种输入模态的弱监督。这种额外的模态可以作为距离直接结合到流行的基于三重态的损失函数中。最近,分类损失和基于代理的度量学习已经被观察到导致更快的收敛以及更好的检索结果,而不需要复杂和昂贵的采样策略。在本文中,我们提出了一种对现有自适应余量的扩展,用于基于分类的深度度量学习。我们的扩展为每个样本的每个负代理引入了一个单独的保证金。这些边界是在训练期间根据其他模态中的类的预先计算的距离来计算的。我们的结果在亚马逊时尚检索数据集和公共DeepFashion数据集上都建立了新的最先进的技术。这在基于fastText和BERT的嵌入中观察到,用于额外的文本模态。我们的结果是实现了更快的收敛速度和更低的代码复杂度比现有的国家的最先进的。

英文摘要:

Recent works have shown that deep metric learning algorithms can benefit from weak supervision from another input modality. This additional modality can be incorporated directly into the popular triplet-based loss function as distances. Also recently, classification loss and proxy-based metric learning have been observed to lead to faster convergence as well as better retrieval results, all the while without requiring complex and costly sampling strategies. In this paper we propose an extension to the existing adaptive margin for classification-based deep metric learning. Our extension introduces a separate margin for each negative proxy per sample. These margins are computed during training from precomputed distances of the classes in the other modality. Our results set a new state-of-the-art on both on the Amazon fashion retrieval dataset as well as on the public DeepFashion dataset. This was observed with both fastText- and BERT-based embeddings for the additional textual modality. Our results were achieved with faster convergence and lower code complexity than the prior state-of-the-art.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑