One of the main purposes of deep metric learning is to construct an embedding space that has well-generalized embeddings on both seen (training) classes and unseen (test) classes. Most existing works have tried to achieve this using different types of metric objectives and hard sample mining strategies with given training data. However, learning with only the training data can be overfitted to the seen classes, leading to the lack of generalization capability on unseen classes. To address this problem, we propose a simple regularizer called Proxy Synthesis that exploits synthetic classes for stronger generalization in deep metric learning. The proposed method generates synthetic embeddings and proxies that work as synthetic classes, and they mimic unseen classes when computing proxy-based losses. Proxy Synthesis derives an embedding space considering class relations and smooth decision boundaries for robustness on unseen classes. Our method is applicable to any proxy-based losses, including softmax and its variants. Extensive experiments on four famous benchmarks in image retrieval tasks demonstrate that Proxy Synthesis significantly boosts the performance of proxy-based losses and achieves state-of-the-art performance.
翻译:深入的衡量学习的主要目的之一是构建一个嵌入空间,在可见(培训)班级和无形(测试)班级上广泛嵌入。大多数现有工程都试图利用不同类型的衡量目标和硬抽样采矿战略来实现这一目标。然而,仅以培训数据来进行学习,可能与所见班级不相称,导致缺乏对看不见班级的普遍化能力。为解决这一问题,我们建议使用一个简单的正规化器,即 " 普罗克西合成 ",利用合成班,在深度计量学习中更全面地普及。拟议方法产生合成嵌入和代理,作为合成班,在计算代用损失时模仿隐蔽班级。代理合成生成了一个嵌入空间,考虑到班级关系和顺利决定界限,以稳健。我们的方法适用于任何代用损失,包括软轴及其变体。在图像检索任务中的四项著名基准上进行的广泛实验表明,代用合成班级大大提升了代用损失的绩效,并取得了最新业绩。