We present a Momentum Re-identification (MoReID) framework that can leverage a very large number of negative samples in training for general re-identification task. The design of this framework is inspired by Momentum Contrast (MoCo), which uses a dictionary to store current and past batches to build a large set of encoded samples. As we find it less effective to use past positive samples which may be highly inconsistent to the encoded feature property formed with the current positive samples, MoReID is designed to use only a large number of negative samples stored in the dictionary. However, if we train the model using the widely used Triplet loss that uses only one sample to represent a set of positive/negative samples, it is hard to effectively leverage the enlarged set of negative samples acquired by the MoReID framework. To maximize the advantage of using the scaled-up negative sample set, we newly introduce Hard-distance Elastic loss (HE loss), which is capable of using more than one hard sample to represent a large number of samples. Our experiments demonstrate that a large number of negative samples provided by MoReID framework can be utilized at full capacity only with the HE loss, achieving the state-of-the-art accuracy on three re-ID benchmarks, VeRi-776, Market-1501, and VeRi-Wild.
翻译:我们提出了一个动态再识别(MoreID)框架,该框架可以在一般再识别任务的培训中利用大量负面样本。这个框架的设计受Momentum Contrast (MoCo)的启发,它使用字典存储当前和过去的批量,以建立大量的编码样本。我们发现,使用以往的正样并不那么有效,而过去的正样可能与当前正样所形成的编码特征属性高度不一致,因此,该部的设计只能使用在字典中储存的大量负面样本。然而,如果我们使用广泛使用的Triplet损失模型来培训模型,而该模型只使用一个样本来代表一组正反面样本,那么很难有效地利用由MoReID框架获取的扩大的一组负面样本来储存大量。为了最大限度地利用扩大的负面样本的优势,我们新引入了硬距离 Elatic损失(HE),这能够使用一个以上的硬样,代表大量样本。我们的实验表明,只有利用IM框架提供的大量负面样本才能在全部能力上利用VERM-7,只有ER-VEM-71和VEM-VEM-7的准确性标尺,才能在VEM-37的精确度上使用。