Compatible features enable the direct comparison of old and new learned features allowing to use them interchangeably over time. In visual search systems, this eliminates the need to extract new features from the gallery-set when the representation model is upgraded with novel data. This has a big value in real applications as re-indexing the gallery-set can be computationally expensive when the gallery-set is large, or even infeasible due to privacy or other concerns of the application. In this paper, we propose CoReS, a new training procedure to learn representations that are \textit{compatible} with those previously learned, grounding on the stationarity of the features as provided by fixed classifiers based on polytopes. With this solution, classes are maximally separated in the representation space and maintain their spatial configuration stationary as new classes are added, so that there is no need to learn any mappings between representations nor to impose pairwise training with the previously learned model. We demonstrate that our training procedure largely outperforms the current state of the art and is particularly effective in the case of multiple upgrades of the training-set, which is the typical case in real applications.

翻译：兼容特征使得新旧学习特征可以直接比较，从而允许它们随时间相互替换使用。在视觉搜索系统中，当使用新数据升级表示模型时，无需从图像库中重新提取新特征。这在现实应用中具有重要价值，因为当图像库规模较大时，重新索引图像库可能计算成本高昂，甚至因隐私或其他应用问题而不可行。本文提出CoReS——一种基于多面体固定分类器提供的特征平稳性来学习与先前学习特征兼容的表示的新训练流程。该方案使类别在表示空间中得到最大程度的分离，并在添加新类别时保持其空间配置稳定，因此既无需学习表征之间的任何映射，也无需与先前学习的模型进行成对训练。实验证明，本训练方法大幅优于当前最先进技术，在训练集多次升级（实际应用中的典型情况）时尤为有效。