Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization
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.
PDF Abstract ECCV 2020 PDF ECCV 2020 Abstract
ImageNet
PACS
Results from the Paper
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Anomaly Detection | MVTec AD Textures Domain Generalization | EISNet+ | Detection AUROC | 90.9 | # 3 | |
| Domain Generalization | PACS | EISNet (Resnet-50) | Average Accuracy | 85.84 | # 41 | |
| Domain Generalization | PACS | EISNet (Resnet-18) | Average Accuracy | 82.15 | # 71 |
