Several studies have compared the in-distribution (ID) and out-ofdistribution (OOD) performance of models in computer vision and NLP. They report a frequent positive correlation, but surprisingly, almost never an inverse correlation that would be indicative of a necessary trade-off. Such inverse patterns are possible theoretically, and their occurrence in practice is important to determine whether ID performance can serve as a proxy for OOD generalization.

Since out-of-distribution generalization is a generally ill-posed problem, various proxy targets (e.g., calibration, adversarial robustness, algorithmic corruptions, invariance across shifts) were studied across different research programs resulting in different recommendations. While sharing the same aspirational goal, these approaches have never been tested under the same experimental conditions on real data. In this paper, we take a unified view of previous work, highlighting message discrepancies that we address empirically, and providing recommendations on how to measure the robustness of a model and how to improve it. To this end, we collect 172 publicly available dataset pairs for training and out-of-distribution evaluation of accuracy, calibration error, adversarial attacks, environment invariance, and synthetic corruptions.

While Vision Transformer (ViT) have achieved success across various machine learning tasks, deploying them in real-world scenarios faces a critical challenge: generalizing under Out-of-Distribution (OoD) shifts. A crucial research gap remains in understanding how to design ViT architectures - both manually and automatically - to excel in OoD generalization.

When fine-tuning zero-shot models like CLIP, our desideratum is for the fine-tuned model to excel in both in-distribution (ID) and out-of-distribution (OOD). Recently, ensemble-based models (ESM) have been shown to offer significant robustness improvement, while preserving high ID accuracy. However, our study finds that ESMs do not solve the ID-OOD trade-offs: they achieve peak performance for ID and OOD accuracy at different mixing coefficients. When optimized for OOD accuracy, the ensemble model exhibits a noticeable decline in ID accuracy, and vice versa. In contrast, we propose a sample-wise ensembling technique that can simultaneously attain the best ID and OOD accuracy without the trade-offs.

"Effective robustness" measures the extra out-of-distribution (OOD) robustness