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:现实世界视觉搜索系统涉及在多个平台上部署具有不同计算和储存资源的多功能平台。 部署适合最小封闭平台的统一模型导致的准确性有限。 预计将部署能力不同、适应资源制约的模型, 要求这些模型所提取的特征在计量空间中保持一致。 实现特征匹配的方法被称为“ 兼容学习 ” 。 现有的研究主要侧重于一个对一个兼容的模型, 它在多个模型的学习兼容性方面受到限制。 我们提出一个具有自相容性的可转换代表性学习框架( SFSC ) 。 SFSC 通过一个培训进程生成了一系列具有不同能力的兼容子模型。 优化子模型将面临梯度冲突, 我们从规模和方向的角度来缓解这一问题。 我们通过不确定性的估算来动态调整子模型的优先事项, 以便恰当地共同优化子模型。 此外, 预测具有相互矛盾方向的梯度将避免相互干扰。 SFSC 在评估的数据集上实现最先进的性能 。</s>