Real-world visual search systems involve deployments on multiple platforms with different computing and storage resources. Deploying a unified model that suits the minimal-constrain platforms leads to limited accuracy. It is expected to deploy models with different capacities adapting to the resource constraints, which requires features extracted by these models to be aligned in the metric space. The method to achieve feature alignments is called ``compatible learning''. Existing research mainly focuses on the one-to-one compatible paradigm, which is limited in learning compatibility among multiple models. We propose a Switchable representation learning Framework with Self-Compatibility (SFSC). SFSC generates a series of compatible sub-models with different capacities through one training process. The optimization of sub-models faces gradients conflict, and we mitigate this problem from the perspective of the magnitude and direction. We adjust the priorities of sub-models dynamically through uncertainty estimation to co-optimize sub-models properly. Besides, the gradients with conflicting directions are projected to avoid mutual interference. SFSC achieves state-of-the-art performance on the evaluated datasets.

翻译：摘要：现实世界中的视觉搜索系统涉及在具有不同计算和存储资源的多个平台上部署。部署适配最低约束平台的统一模型会导致精度受限。理想的做法是根据资源约束部署不同容量的模型，这要求这些模型提取的特征在度量空间中保持对齐。实现特征对齐的方法称为"兼容学习"。现有研究主要聚焦于一对一的兼容范式，在实现多模型间的兼容性学习方面存在局限。本文提出一种具备自兼容性的可切换表示学习框架（SFSC）。SFSC通过单次训练过程生成一系列具备不同容量的兼容子模型。子模型优化面临梯度冲突问题，我们从幅度与方向两个维度缓解这一矛盾。通过不确定性估计动态调整子模型的优先级，以实现子模型的合理协同优化。此外，对方向冲突的梯度进行投影以避免相互干扰。SFSC在多个评估数据集上均取得了最先进的性能。