paper-with-me

Papers

SimpleDG: Simple Domain Generalization Baseline without Bells and Whistles

2022-10-26 · Zhi Lv, Bo Lin, Siyuan Liang, Lihua Wang, Mochen Yu, Yao Tang, Jiajun Liang

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

📄 PDF Abstract BibTeX arXiv:2210.14507

Code (1)

megvii-research/simpledg 공식 구현 pytorch

Tasks

Domain Generalization

Similar Papers 제목 키워드 기반

Simple Domain Generalization Methods are Strong Baselines for Open Domain Generalization

2023-03-31 · Masashi Noguchi, Shinichi Shirakawa

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+1

Multi-Domain Balanced Sampling Improves Out-of-Distribution Generalization of Chest X-ray Pathology Prediction Models

2021-12-27 · Enoch Tetteh, Joseph Viviano, Yoshua Bengio, David Krueger 외

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 Learning

Augmentation-based Domain Generalization for Semantic Segmentation

2023-04-24 · Manuel Schwonberg, Fadoua El Bouazati, Nico M. Schmidt, Hanno Gottschalk

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 Adaptation

ERM++: An Improved Baseline for Domain Generalization

2023-04-04 · Piotr Teterwak, Kuniaki Saito, Theodoros Tsiligkaridis, Kate Saenko 외

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 Generalization

Rethinking Domain Generalization Baselines

2021-01-22 · Francesco Cappio Borlino, Antonio D'Innocente, Tatiana Tommasi

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