Deep Neural Networks (DNNs) have become pivotal in various fields, especially in computer vision, outperforming previous methodologies. A critical challenge in their deployment is the bias inherent in data across different domains, such as image style, and environmental conditions, leading to domain gaps. This necessitates techniques for learning general representations from biased training data, known as domain generalization. This paper presents Attend to eXpert Prompts (A2XP), a novel approach for domain generalization that preserves the privacy and integrity of the network architecture. A2XP consists of two phases: Expert Adaptation and Domain Generalization. In the first phase, prompts for each source domain are optimized to guide the model towards the optimal direction. In the second phase, two embedder networks are trained to effectively amalgamate these expert prompts, aiming for an optimal output. Our extensive experiments demonstrate that A2XP achieves state-of-the-art results over existing non-private domain generalization methods. The experimental results validate that the proposed approach not only tackles the domain generalization challenge in DNNs but also offers a privacy-preserving, efficient solution to the broader field of computer vision.

翻译：深度神经网络（DNNs）已在多个领域，尤其是计算机视觉中，展现出超越以往方法的关键作用。其部署过程中面临的核心挑战是不同域（如图像风格和环境条件）间数据固有的偏差，这导致了域间隙。因此需要从有偏训练数据中学习通用表征的技术，即域泛化。本文提出了"关注专家提示"（Attend to eXpert Prompts, A2XP）方法，这是一种在保护网络架构隐私与完整性的前提下实现域泛化的创新方案。A2XP包含两个阶段：专家适应与域泛化。第一阶段，优化每个源域的提示以引导模型朝向最优方向；第二阶段，训练两个嵌入网络有效融合这些专家提示，追求最优输出。大量实验表明，A2XP在现有非私有域泛化方法中取得了最优结果。实验结果验证了所提方法不仅解决了DNNs中的域泛化挑战，还为计算机视觉领域提供了兼顾隐私保护与高效性的解决方案。