Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization
This work addresses the problem of improving neural network generalization across domains for real-world applications, representing an incremental advance.
The paper tackled domain generalization in object recognition by proposing a framework that combines extrinsic relationship supervision and intrinsic self-supervision, achieving state-of-the-art performance on VLCS and PACS benchmarks.
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.