The generalization capability of neural networks across domains is crucial
for real-world applications. We argue that a generalized object recognition
system should well understand the relationships among different images and also
the images themselves at the same time. To this end, we present a new domain
generalization framework that learns how to generalize across domains
simultaneously from extrinsic relationship supervision and intrinsic
self-supervision for images from multi-source domains. To be specific, we
formulate our framework with feature embedding using a multi-task learning
paradigm. Besides conducting the common supervised recognition task, we
seamlessly integrate a momentum metric learning task and a self-supervised
auxiliary task to collectively utilize the extrinsic supervision and intrinsic
supervision. Also, we develop an effective momentum metric learning scheme with
K-hard negative mining to boost the network to capture image relationship for
domain generalization. We demonstrate the effectiveness of our approach on two
standard object recognition benchmarks VLCS and PACS, and show that our methods
achieve state-of-the-art performance.

提出了一种基于神经网络的领域泛化框架，它使用多任务学习范式的特征嵌入形式，在进行普通的监督识别任务的同时，还无缝集成了动量度量学习任务和自我监督辅助任务，以共同利用外部监督和内在监督，并通过使用 K-hard 负采样的有效动量度量学习方案，来提升网络的性能。对 VLCS 和 PACS 两个标准目标识别基准进行测试，结果表明该方法达到了最先进的性能表现。