论文标题
负样本很大：利用硬距离弹性损失进行重新识别
Negative Samples are at Large: Leveraging Hard-distance Elastic Loss for Re-identification
论文作者
论文摘要
我们提出了一个动力重新识别（莫雷德）框架，该框架可以利用大量的负面样本来进行一般重新识别任务。该框架的设计灵感来自动量对比度（MOCO），该对比度（MOCO）使用词典来存储当前和过去的批次来构建大量编码样品。由于我们发现使用过去的阳性样品与当前正面样品形成的编码特征属性高度不一致是有效的，因此莫雷德（Moreid）设计仅使用词典中存储的大量负样品。但是，如果我们使用仅使用一个样品代表一组正/负样本的广泛使用的三胞胎损失来训练该模型，则很难有效利用莫比德框架获得的扩大的负面样品集。为了最大程度地利用扩展的负面样品集的优势，我们新引入强距离弹性损失（HE损失），该损失能够使用多个硬样品代表大量样品。我们的实验表明，只有在HE损失的情况下，才能全力利用大量由Moreid框架提供的负面样本，从而在三个重新ID基准测试基准（VERI-776，Market-1501和Veri-Wild）上达到最先进的准确性。
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.
