SimpleDG: Simple Domain Generalization Baseline without Bells and Whistles
We present a simple domain generalization baseline, which wins second place in both the common context generalization track and the hybrid context generalization track respectively in NICO CHALLENGE 2022. We verify the founding in recent literature, domainbed, that ERM is a strong baseline compared to recent state-of-the-art domain generalization methods and propose SimpleDG which includes several simple yet effective designs that further boost generalization performance. Code is available at https://github.com/megvii-research/SimpleDG
Code (1)
Tasks
Domain GeneralizationSimilar Papers 제목 키워드 기반
Simple Domain Generalization Methods are Strong Baselines for Open Domain Generalization
In real-world applications, a machine learning model is required to handle an open-set recognition (OSR), where unknown classes appear during the inference, in addition to a domain shift, where the distribution of data d…
Data AugmentationDomain GeneralizationEnsemble LearningMeta-Learning+1Multi-Domain Balanced Sampling Improves Out-of-Distribution Generalization of Chest X-ray Pathology Prediction Models
Learning models that generalize under different distribution shifts in medical imaging has been a long-standing research challenge. There have been several proposals for efficient and robust visual representation learnin…
Out-of-Distribution GeneralizationRepresentation LearningAugmentation-based Domain Generalization for Semantic Segmentation
Unsupervised Domain Adaptation (UDA) and domain generalization (DG) are two research areas that aim to tackle the lack of generalization of Deep Neural Networks (DNNs) towards unseen domains. While UDA methods have acces…
Domain AdaptationDomain GeneralizationSemantic SegmentationUnsupervised Domain AdaptationERM++: An Improved Baseline for Domain Generalization
Domain Generalization (DG) aims to develop classifiers that can generalize to new, unseen data distributions, a critical capability when collecting new domain-specific data is impractical. A common DG baseline minimizes …
Domain GeneralizationRethinking Domain Generalization Baselines
Despite being very powerful in standard learning settings, deep learning models can be extremely brittle when deployed in scenarios different from those on which they were trained. Domain generalization methods investiga…
Data AugmentationDomain GeneralizationStyle Transfer