A Meta-Analysis of Distributionally-Robust Models
Not on the map. Why?
Abstract (arXiv)
State-of-the-art image classifiers trained on massive datasets (such as ImageNet) have been shown to be vulnerable to a range of both intentional and incidental distribution shifts. On the other hand, several recent classifiers with favorable out-of-distribution (OOD) robustness properties have emerged, achieving high accuracy on their target tasks while maintaining their in-distribution accuracy on challenging benchmarks. We present a meta-analysis on a wide range of publicly released models, most of which have been published over the last twelve months. Through this meta-analysis, we empirically identify four main commonalities for all the best-performing OOD-robust models, all of which illuminate the considerable promise of vision-language pre-training.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 21 of its 27 references that are in the map. First posted on arXiv 15 Jun 2022.
Builds on
21 of 27 references.
References · 21
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
- 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
- 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
- 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
- 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
- 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
- 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
- 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
- 2019Learning Robust Global Representations by Penalizing Local Predictive Powercited by 1,010
- 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
- 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
9 more
- 2020Measuring Robustness to Natural Distribution Shifts in Image Classificationcited by 452
- 2021SLIP: Self-supervision meets Language-Image Pre-trainingcited by 434
- 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 248
- 2021Partial success in closing the gap between human and machine visioncited by 185
- 2021Combined Scaling for Zero-shot Transfer Learningcited by 182
- 2020An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Modelscited by 133
- 2016Learning Visual N-Grams from Web Datacited by 95
- 2022Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervisioncited by 80
- 2021Comparing Popular Simulation Environments in the Scope of Robotics and Reinforcement Learningcited by 10
Built on by
Citing papers per year: 2022: 1; 2023: 1.
2 papers.
- 2022Caption supervision enables robust learnerscited by 4
- 2023Distributionally Robust Classification on a Data Budgetcited by 2
- 2023Distributionally Robust Classification on a Data Budget7 Aug 2023
- 2022Caption supervision enables robust learners13 Oct 2022
Similar, not cited
Close in wording, no citation either way
- 2025A Benchmark and Evaluation for Real-World Out-of-Distribution Detection Using Vision-Language Models
- 2025LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models
- 2025CNS-Bench: Benchmarking Image Classifier Robustness Under Continuous Nuisance Shifts
- 2024Open-Vocabulary Object Detectors: Robustness Challenges under Distribution Shifts
- 2023Towards Calibrated Robust Fine-Tuning of Vision-Language Models
- 2023On the Powerfulness of Textual Outlier Exposure for Visual OoD Detection
- 2025Delving into Out-of-Distribution Detection with Medical Vision-Language Models
- 2023Class Relevance Learning For Out-of-distribution Detection