In Search of Lost Domain Generalization

Gulrajani, Ishaan; López-Paz, David

doi:10.48550/arxiv.2007.01434

Cited by 105 publications

(264 citation statements)

References 23 publications

Supporting

Mentioning

256

Contrasting

Order By: Relevance

“…Examples of these methods include Multi-source Domain Adversarial Networks (MDAN) (Zhao et al, 2018) and Moment Matching for Multi-Source Domain Adaptation (M3SDA) (Peng et al, 2019). The DomainBed (Gulrajani and Lopez-Paz, 2020) and WILDS (Koh et al, 2021) benchmarks also extended singlesource algorithms like CORAL and DANN to take advantage of multiple source domains in the domain generalization setting, and similar extensions in the domain adaptation setting could be promising.…”

Section: B2 Domain-invariant Methodsmentioning

confidence: 99%

Extending the WILDS Benchmark for Unsupervised Adaptation

Sagawa¹,

Koh²,

Lee³

et al. 2021

Preprint

View full text Add to dashboard Cite

Machine learning systems deployed in the wild are often trained on a source distribution but deployed on a different target distribution. Unlabeled data can be a powerful point of leverage for mitigating these distribution shifts, as it is frequently much more available than labeled data. However, existing distribution shift benchmarks for unlabeled data do not reflect the breadth of scenarios that arise in real-world applications. In this work, we present the Wilds 2.0 update, which extends 8 of the 10 datasets in the Wilds benchmark of distribution shifts to include curated unlabeled data that would be realistically obtainable in deployment. To maintain consistency, the labeled training, validation, and test sets, as well as the evaluation metrics, are exactly the same as in the original Wilds benchmark. These datasets span a wide range of applications (from histology to wildlife conservation), tasks (classification, regression, and detection), and modalities (photos, satellite images, microscope slides, text, molecular graphs). We systematically benchmark state-of-the-art methods that leverage unlabeled data, including domain-invariant, self-training, and self-supervised methods, and show that their success on Wilds is limited. To facilitate method development and evaluation, we provide an open-source package that automates data loading and contains all of the model architectures and methods used in this paper. Code and leaderboards are available at https://wilds.stanford.edu.

show abstract

Section: B2 Domain-invariant Methodsmentioning

confidence: 99%

Extending the WILDS Benchmark for Unsupervised Adaptation

Sagawa¹,

Koh²,

Lee³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Few preliminary efforts have been made to explore this direction [438]; however, the work is still in its infancy and requires further attention from the community. Further, standardized and rigorous evaluation protocols also need to be established for domain adaptation in the medical imaging applications, similar to DOMAINBED [439] framework in the natural image domain. Such a framework will also help in advocating models reproducibility.…”

Section: Domain Adaptation and Out-of-distribution Detectionmentioning

confidence: 99%

Transformers in Medical Imaging: A Survey

Shamshad¹,

Khan²,

Zamir³

et al. 2022

Preprint

View full text Add to dashboard Cite

Following unprecedented success on the natural language tasks, Transformers have been successfully applied to several computer vision problems, achieving state-of-the-art results and prompting researchers to reconsider the supremacy of convolutional neural networks (CNNs) as de facto operators. Capitalizing on these advances in computer vision, the medical imaging field has also witnessed growing interest for Transformers that can capture global context compared to CNNs with local receptive fields. Inspired from this transition, in this survey, we attempt to provide a comprehensive review of the applications of Transformers in medical imaging covering various aspects, ranging from recently proposed architectural designs to unsolved issues. Specifically, we survey the use of Transformers in medical image segmentation, detection, classification, reconstruction, synthesis, registration, clinical report generation, and other tasks. In particular, for each of these applications, we develop taxonomy, identify application-specific challenges as well as provide insights to solve them, and highlight recent trends. Further, we provide a critical discussion of the field's current state as a whole, including the identification of key challenges, open problems, and outlining promising future directions. We hope this survey will ignite further interest in the community and provide researchers with an up-to-date reference regarding applications of Transformer models in medical imaging. Finally, to cope with the rapid development in this field, we intend to regularly update the relevant latest papers and their open-source implementations at https://github.com/fahadshamshad/awesome-transformers-in-medical-imaging.

show abstract

“…The featurizer is φ, trained purely on the unsupervised game. The classifier is w, trained purely on the downstream supervised task [3].…”

Section: Self-supervised Learningmentioning

confidence: 99%

CELESTIAL: Classification Enabled via Labelless Embeddings with Self-supervised Telescope Image Analysis Learning

Kotha¹,

Koul²,

Ganju³

et al. 2022

Preprint

View full text Add to dashboard Cite

A common class of problems in remote sensing is scene classification, a fundamentally important task for natural hazards identification, geographic image retrieval, and environment monitoring. Recent developments in this field rely label-dependent supervised learning techniques which is antithetical to the 35 petabytes of unlabelled satellite imagery in NASA GIBS. To solve this problem, we establish CELESTIAL-a self-supervised learning pipeline for effectively leveraging sparsely-labeled satellite imagery. This pipeline successfully adapts SimCLR, an algorithm that first learns image representations on unlabelled data and then fine-tunes this knowledge on the provided labels. Our results show CELESTIAL requires only a third of the labels that the supervised method needs to attain the same accuracy on an experimental dataset. The first unsupervised tier can enable applications such as reverse image search for NASA Worldview (i.e. searching similar atmospheric phenomenon over years of unlabelled data with minimal samples) and the second supervised tier can lower the necessity of expensive data annotation significantly. In the future, we hope we can generalize the CELESTIAL pipeline to other data types, algorithms, and applications.

show abstract

In Search of Lost Domain Generalization

Cited by 105 publications

References 23 publications

Extending the WILDS Benchmark for Unsupervised Adaptation

Extending the WILDS Benchmark for Unsupervised Adaptation

Transformers in Medical Imaging: A Survey

CELESTIAL: Classification Enabled via Labelless Embeddings with Self-supervised Telescope Image Analysis Learning

Contact Info

Product

Resources

About