Image retrieval plays an important role in the Internet world. Usually, the core parts of mainstream visual retrieval systems include an online service of the embedding model and a large-scale vector database. For traditional model upgrades, the old model will not be replaced by the new one until the embeddings of all the images in the database are re-computed by the new model, which takes days or weeks for a large amount of data. Recently, backward-compatible training (BCT) enables the new model to be immediately deployed online by making the new embeddings directly comparable to the old ones. For BCT, improving the compatibility of two models with less negative impact on retrieval performance is the key challenge. In this paper, we introduce AdvBCT, an Adversarial Backward-Compatible Training method with an elastic boundary constraint that takes both compatibility and discrimination into consideration. We first employ adversarial learning to minimize the distribution disparity between embeddings of the new model and the old model. Meanwhile, we add an elastic boundary constraint during training to improve compatibility and discrimination efficiently. Extensive experiments on GLDv2, Revisited Oxford (ROxford), and Revisited Paris (RParis) demonstrate that our method outperforms other BCT methods on both compatibility and discrimination. The implementation of AdvBCT will be publicly available at https://github.com/Ashespt/AdvBCT.

翻译：图像检索在互联网世界中扮演着重要角色。通常，主流视觉检索系统的核心组件包括嵌入模型的在线服务与大规模向量数据库。对于传统模型升级，旧模型必须等到数据库中所有图像的嵌入由新模型重新计算后才能被替换，这一过程对于海量数据可能需要数天或数周时间。最近提出的后向兼容训练（BCT）通过使新嵌入直接与旧嵌入可比，实现了新模型的即时在线部署。对于BCT而言，如何提升两个模型间的兼容性，同时减少对检索性能的负面影响，是核心挑战。本文提出AdvBCT——一种具有弹性边界约束的抗性后向兼容训练方法，同时兼顾兼容性与区分性。我们首先采用抗性学习来最小化新模型与旧模型嵌入之间的分布差异。同时，在训练过程中引入弹性边界约束，以高效提升兼容性与区分性。在GLDv2、Revisited Oxford（ROxford）和Revisited Paris（RParis）上的大量实验表明，我们的方法在兼容性与区分性上均优于其他BCT方法。AdvBCT的实现将在https://github.com/Ashespt/AdvBCT公开。