当前位置: X-MOL 学术IEEE Trans. Image Process. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Deep Adversarial Metric Learning.
IEEE Transactions on Image Processing ( IF 10.8 ) Pub Date : 2019-10-25 , DOI: 10.1109/tip.2019.2948472
Yueqi Duan , Jiwen Lu , Wenzhao Zheng , Jie Zhou

Learning an effective distance measurement between sample pairs plays an important role in visual analysis, where the training procedure largely relies on hard negative samples. However, hard negative samples usually account for the tiny minority in the training set, which may fail to fully describe the data distribution close to the decision boundary. In this paper, we present a deep adversarial metric learning (DAML) framework to generate synthetic hard negatives from the original negative samples, which is widely applicable to existing supervised deep metric learning algorithms. Different from existing sampling strategies which simply ignore numerous easy negatives, our DAML aim to exploit them by generating synthetic hard negatives adversarial to the learned metric as complements. We simultaneously train the feature embedding and hard negative generator in an adversarial manner, so that adequate and targeted synthetic hard negatives are created to learn more precise distance metrics. As a single transformation may not be powerful enough to describe the global input space under the attack of the hard negative generator, we further propose a deep adversarial multi-metric learning (DAMML) method by learning multiple local transformations for more complete description. We simultaneously exploit the collaborative and competitive relationships among multiple metrics, where the metrics display unity against the generator for effective distance measurement as well as compete for more training data through a metric discriminator to avoid overlapping. Extensive experimental results on five benchmark datasets show that our DAML and DAMML effectively boost the performance of existing deep metric learning approaches through adversarial learning.

中文翻译:

深度对抗度量学习。

学习样本对之间的有效距离测量值在视觉分析中起着重要作用,在视觉分析中,训练过程主要依赖于硬质阴性样本。但是,硬阴性样本通常占训练集中的一小部分,这可能无法完全描述靠近决策边界的数据分布。在本文中,我们提出了一种深度对抗度量学习(DAML)框架,该框架可从原始负样本中生成合成硬负片,该框架可广泛应用于现有的监督深度度量学习算法。与现有的采样策略(仅忽略众多易用的底片)不同,我们的DAML旨在通过生成与学习的指标对抗的合成硬底片来对它们进行补充。我们以对抗的方式同时训练特征嵌入和硬底片生成器,以便创建足够的目标合成硬底片以学习更精确的距离度量。由于单个转换可能不足以在硬否定生成器的攻击下描述全局输入空间,因此我们通过学习多个局部转换来进一步提出一种深度对抗多度量学习(DAMML)方法,以进行更完整的描述。我们同时利用多个度量标准之间的协作和竞争关系,其中度量标准相对于生成器显示统一性,以进行有效的距离测量,并通过度量标准判别器竞争更多的训练数据,以避免重叠。
更新日期:2020-04-22
down
wechat
bug