# Robustness properties of Facebook's ResNeXt WSL models

arXiv: https://arxiv.org/abs/1907.07640 · HTML: https://mlsanity.com/paper/1907.07640/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2019.

## Built on by (most cited first, 17 of 17)

- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [MEMO: Test Time Robustness via Adaptation and Augmentation](https://mlsanity.com/paper/2110.09506/) (2021)
- [3D Common Corruptions and Data Augmentation](https://mlsanity.com/paper/2203.01441/) (2022)
- [On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness](https://mlsanity.com/paper/2102.11273/) (2021)
- [Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection](https://mlsanity.com/paper/2101.03778/) (2021)
- [Understanding Softmax Confidence and Uncertainty](https://mlsanity.com/paper/2106.04972/) (2021)
- [Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training](https://mlsanity.com/paper/2106.08616/) (2021)
- [Improving robustness against common corruptions with frequency biased models](https://mlsanity.com/paper/2103.16241/) (2021)
- [Do better ImageNet classifiers assess perceptual similarity better?](https://mlsanity.com/paper/2203.04946/) (2022)
- [Reading Isn't Believing: Adversarial Attacks On Multi-Modal Neurons](https://mlsanity.com/paper/2103.10480/) (2021)
- [Foundation Model-oriented Robustness: Robust Image Model Evaluation with Pretrained Models](https://mlsanity.com/paper/2308.10632/) (2023)
- [Compositional generalization in semantic parsing with pretrained transformers](https://mlsanity.com/paper/2109.15101/) (2021)
- [Adapt in the Wild: Test-Time Entropy Minimization with Sharpness and Feature Regularization](https://mlsanity.com/paper/2509.04977/) (2025)
- [Improved Out-of-Scope Intent Classification with Dual Encoding and Threshold-based Re-Classification](https://mlsanity.com/paper/2405.19967/) (2024)
- [Decoupling Stability and Plasticity for Multi-Modal Test-Time Adaptation](https://mlsanity.com/paper/2603.00574/) (2026)
- [Deep Residual Axial Networks](https://mlsanity.com/paper/2301.04631/) (2023)
- [Class-Invariant Test-Time Augmentation for Domain Generalization](https://mlsanity.com/paper/2509.14420/) (2025)

## Abstract (arXiv)

We investigate the robustness properties of ResNeXt class image recognition models trained with billion scale weakly supervised data (ResNeXt WSL models). These models, recently made public by Facebook AI, were trained with ~1B images from Instagram and fine-tuned on ImageNet. We show that these models display an unprecedented degree of robustness against common image corruptions and perturbations, as measured by the ImageNet-C and ImageNet-P benchmarks. They also achieve substantially improved accuracies on the recently introduced "natural adversarial examples" benchmark (ImageNet-A). The largest of the released models, in particular, achieves state-of-the-art results on ImageNet-C, ImageNet-P, and ImageNet-A by a large margin. The gains on ImageNet-C, ImageNet-P, and ImageNet-A far outpace the gains on ImageNet validation accuracy, suggesting the former as more useful benchmarks to measure further progress in image recognition. Remarkably, the ResNeXt WSL models even achieve a limited degree of adversarial robustness against state-of-the-art white-box attacks (10-step PGD attacks). However, in contrast to adversarially trained models, the robustness of the ResNeXt WSL models rapidly declines with the number of PGD steps, suggesting that these models do not achieve genuine adversarial robustness. Visualization of the learned features also confirms this conclusion. Finally, we show that although the ResNeXt WSL models are more shape-biased than comparable ImageNet-trained models in a shape-texture cue conflict experiment, they still remain much more texture-biased than humans, suggesting that they share some of the underlying characteristics of ImageNet-trained models that make this benchmark challenging.