A Meta-Analysis of Distributionally-Robust Models
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Distributionally robust minimization in meta-learning for system identification
Meta learning aims at learning how to solve tasks, and thus it allows to estimate models that can be quickly adapted to new scenarios. This work explores distributionally robust minimization in meta learning for system i…
Meta-LearningCompositional federated learning: Applications in distributionally robust averaging and meta learning
In the paper, we propose an effective and efficient Compositional Federated Learning (ComFedL) algorithm for solving a new compositional Federated Learning (FL) framework, which frequently appears in many data mining and…
BIG-bench Machine LearningFederated LearningMeta-LearningStochastic OptimizationMeta Learning not to Learn: Robustly Informing Meta-Learning under Nuisance-Varying Families
In settings where both spurious and causal predictors are available, standard neural networks trained under the objective of empirical risk minimization (ERM) with no additional inductive biases tend to have a dependence…
Meta-LearningA Short and General Duality Proof for Wasserstein Distributionally Robust Optimization
We present a general duality result for Wasserstein distributionally robust optimization that holds for any Kantorovich transport cost, measurable loss function, and nominal probability distribution. Assuming an intercha…
A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm
Meta learning is a promising paradigm to enable skill transfer across tasks. Most previous methods employ the empirical risk minimization principle in optimization. However, the resulting worst fast adaptation to a subse…
Meta-Learning