Most deep metric learning (DML) methods employ a strategy that forces all positive samples to be close in the embedding space while keeping them away from negative ones. However, such a strategy ignores the internal relationships of positive (negative) samples and often leads to overfitting, especially in the presence of hard samples and mislabeled samples. In this work, we propose a simple yet effective regularization, namely Listwise Self-Distillation (LSD), which progressively distills a model's own knowledge to adaptively assign a more appropriate distance target to each sample pair in a batch. LSD encourages smoother embeddings and information mining within positive (negative) samples as a way to mitigate overfitting and thus improve generalization. Our LSD can be directly integrated into general DML frameworks. Extensive experiments show that LSD consistently boosts the performance of various metric learning methods on multiple datasets.
翻译:最深入的衡量学习(DML)方法采用了一种战略,迫使所有正样都靠近嵌入空间,同时不让它们靠近负样。然而,这种战略忽视了正(负)样的内缘关系,往往导致过度配制,特别是在硬样和贴错标签的样品出现的情况下。在这项工作中,我们建议简单而有效的规范化,即Listwise自蒸(LSD),逐步提炼模型本身的知识,以适应性地为每对样品分批分配更适当的距离目标。LSD鼓励在正(负)样样品中更平稳地嵌入和信息挖掘,以缓解过度装配,从而改进概括化。我们的LSDD可以直接融入DML框架。广泛的实验表明,LSD在多个数据集上不断提高各种衡量学习方法的性能。