# Assaying Out-Of-Distribution Generalization in Transfer Learning

arXiv: https://arxiv.org/abs/2207.09239 · HTML: https://mlsanity.com/paper/2207.09239/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- Builds on 102 of its 132 references that are in the map.
- First posted on arXiv 19 Jul 2022.

## Builds on (most cited first, 30 of 102)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)

## Built on by (most cited first, 30 of 53)

- [Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization](https://mlsanity.com/paper/2212.10445/) (2022)
- [GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective](https://mlsanity.com/paper/2211.08073/) (2022)
- [ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets](https://mlsanity.com/paper/2209.00613/) (2022)
- [Exploring the Limits of Deep Image Clustering using Pretrained Models](https://mlsanity.com/paper/2303.17896/) (2023)
- [Leveraging sparse and shared feature activations for disentangled representation learning](https://mlsanity.com/paper/2304.07939/) (2023)
- [HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2305.13031/) (2023)
- [On the Challenges and Opportunities in Generative AI](https://mlsanity.com/paper/2403.00025/) (2024)
- [Towards Better Out-of-Distribution Generalization of Neural Algorithmic Reasoning Tasks](https://mlsanity.com/paper/2211.00692/) (2022)
- [RLSbench: Domain Adaptation Under Relaxed Label Shift](https://mlsanity.com/paper/2302.03020/) (2023)
- [POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained models](https://mlsanity.com/paper/2305.00350/) (2023)
- [RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization](https://mlsanity.com/paper/2307.10224/) (2023)
- [Tuning Multi-mode Token-level Prompt Alignment across Modalities](https://mlsanity.com/paper/2309.13847/) (2023)
- [Robustifying Token Attention for Vision Transformers](https://mlsanity.com/paper/2303.11126/) (2023)
- [Neuromorphic Visual Scene Understanding with Resonator Networks](https://mlsanity.com/paper/2208.12880/) (2022)
- [Structure-based out-of-distribution (OOD) materials property prediction: a benchmark study](https://mlsanity.com/paper/2401.08032/) (2024)
- [Subgraph Pooling: Tackling Negative Transfer on Graphs](https://mlsanity.com/paper/2402.08907/) (2024)
- [On Catastrophic Inheritance of Large Foundation Models](https://mlsanity.com/paper/2402.01909/) (2024)
- [How Reliable is Your Regression Model's Uncertainty Under Real-World Distribution Shifts?](https://mlsanity.com/paper/2302.03679/) (2023)
- [Image retrieval outperforms diffusion models on data augmentation](https://mlsanity.com/paper/2304.10253/) (2023)
- [A Framework for Efficient Model Evaluation through Stratification, Sampling, and Estimation](https://mlsanity.com/paper/2406.07320/) (2024)
- [What Variables Affect Out-of-Distribution Generalization in Pretrained Models?](https://mlsanity.com/paper/2405.15018/) (2024)
- [Evaluating the Fairness of Discriminative Foundation Models in Computer Vision](https://mlsanity.com/paper/2310.11867/) (2023)
- [Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line](https://mlsanity.com/paper/2310.04941/) (2023)
- [On the Generalization of Handwritten Text Recognition Models](https://mlsanity.com/paper/2411.17332/) (2024)
- [Accuracy on the wrong line: On the pitfalls of noisy data for out-of-distribution generalisation](https://mlsanity.com/paper/2406.19049/) (2024)
- [Robust Representation Learning with Reliable Pseudo-labels Generation via Self-Adaptive Optimal Transport for Short Text Clustering](https://mlsanity.com/paper/2305.16335/) (2023)
- [IBAFormer: Intra-batch Attention Transformer for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2309.06282/) (2023)
- [What Does Softmax Probability Tell Us about Classifiers Ranking Across Diverse Test Conditions?](https://mlsanity.com/paper/2406.09908/) (2024)
- [Meaningful Causal Aggregation and Paradoxical Confounding](https://mlsanity.com/paper/2304.11625/) (2023)
- [BehAVE: Behaviour Alignment of Video Game Encodings](https://mlsanity.com/paper/2402.01335/) (2024)

## Abstract (arXiv)

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. We fine-tune over 31k networks, from nine different architectures in the many- and few-shot setting. Our findings confirm that in- and out-of-distribution accuracies tend to increase jointly, but show that their relation is largely dataset-dependent, and in general more nuanced and more complex than posited by previous, smaller scale studies.