# A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?

arXiv: https://arxiv.org/abs/2112.00639 · HTML: https://mlsanity.com/paper/2112.00639/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 84 references that are in the map.
- First posted on arXiv 1 Dec 2021.

## Builds on (most cited first, 30 of 39)

- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [Measuring Robustness to Natural Distribution Shifts in Image Classification](https://mlsanity.com/paper/2007.00644/) (2020)
- [Making Convolutional Networks Shift-Invariant Again](https://mlsanity.com/paper/1904.11486/) (2019)
- [Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming](https://mlsanity.com/paper/1907.07484/) (2019)
- [Learning to Learn Single Domain Generalization](https://mlsanity.com/paper/2003.13216/) (2020)
- [Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup](https://mlsanity.com/paper/2009.06962/) (2020)
- [Generalisation in humans and deep neural networks](https://mlsanity.com/paper/1808.08750/) (2018)
- [Partial success in closing the gap between human and machine vision](https://mlsanity.com/paper/2106.07411/) (2021)
- [Improving the Robustness of Deep Neural Networks via Stability Training](https://mlsanity.com/paper/1604.04326/) (2016)
- [Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness](https://mlsanity.com/paper/2010.08001/) (2020)
- [Learning Independent Causal Mechanisms](https://mlsanity.com/paper/1712.00961/) (2017)
- [On Robustness and Transferability of Convolutional Neural Networks](https://mlsanity.com/paper/2007.08558/) (2020)
- [A causal framework for distribution generalization](https://mlsanity.com/paper/2006.07433/) (2020)
- [Wavelet Integrated CNNs for Noise-Robust Image Classification](https://mlsanity.com/paper/2005.03337/) (2020)
- [Informative Dropout for Robust Representation Learning: A Shape-bias Perspective](https://mlsanity.com/paper/2008.04254/) (2020)
- [Learning From Brains How to Regularize Machines](https://mlsanity.com/paper/1911.05072/) (2019)
- [What Else Can Fool Deep Learning? Addressing Color Constancy Errors on Deep Neural Network Performance](https://mlsanity.com/paper/1912.06960/) (2019)
- [Multi-level Domain Adaptive learning for Cross-Domain Detection](https://mlsanity.com/paper/1907.11484/) (2019)
- [Are Adversarial Robustness and Common Perturbation Robustness Independent Attributes ?](https://mlsanity.com/paper/1909.02436/) (2019)
- [GradAug: A New Regularization Method for Deep Neural Networks](https://mlsanity.com/paper/2006.07989/) (2020)
- [Addressing Neural Network Robustness with Mixup and Targeted Labeling Adversarial Training](https://mlsanity.com/paper/2008.08384/) (2020)
- [Implicit Saliency in Deep Neural Networks](https://mlsanity.com/paper/2008.01874/) (2020)

## Built on by (most cited first, 30 of 48)

- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction](https://mlsanity.com/paper/2409.00265/) (2024)
- [Are These the Same Apple? Comparing Images Based on Object Intrinsics](https://mlsanity.com/paper/2311.00750/) (2023)
- [MedMNIST-C: Comprehensive benchmark and improved classifier robustness by simulating realistic image corruptions](https://mlsanity.com/paper/2406.17536/) (2024)
- [CaRTS: Causality-driven Robot Tool Segmentation from Vision and Kinematics Data](https://mlsanity.com/paper/2203.09475/) (2022)
- [Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspective](https://mlsanity.com/paper/2407.06992/) (2024)
- [Towards Viewpoint Robustness in Bird's Eye View Segmentation](https://mlsanity.com/paper/2309.05192/) (2023)
- [Ambiguous Images With Human Judgments for Robust Visual Event Classification](https://mlsanity.com/paper/2210.03102/) (2022)
- [Robustness and Cybersecurity in the EU Artificial Intelligence Act](https://mlsanity.com/paper/2502.16184/) (2025)
- [Adversarial Deep Reinforcement Learning for Improving the Robustness of Multi-agent Autonomous Driving Policies](https://mlsanity.com/paper/2112.11937/) (2021)
- [Neural Likelihood Surfaces for Spatial Processes with Computationally Intensive or Intractable Likelihoods](https://mlsanity.com/paper/2305.04634/) (2023)
- [A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligence](https://mlsanity.com/paper/2401.03188/) (2024)
- [A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities](https://mlsanity.com/paper/2210.08906/) (2022)
- [Mind the Graph When Balancing Data for Fairness or Robustness](https://mlsanity.com/paper/2406.17433/) (2024)
- [Machine Learning Robustness: A Primer](https://mlsanity.com/paper/2404.00897/) (2024)
- [SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge](https://mlsanity.com/paper/2407.11906/) (2024)
- [Non-adversarial Robustness of Deep Learning Methods for Computer Vision](https://mlsanity.com/paper/2305.14986/) (2023)
- [RobustCLEVR: A Benchmark and Framework for Evaluating Robustness in Object-centric Learning](https://mlsanity.com/paper/2308.14899/) (2023)
- [SyntheX: Scaling Up Learning-based X-ray Image Analysis Through In Silico Experiments](https://mlsanity.com/paper/2206.06127/) (2022)
- [Rethinking Causality-driven Robot Tool Segmentation with Temporal Constraints](https://mlsanity.com/paper/2212.00072/) (2022)
- [Towards Reliable Evaluation of Neural Program Repair with Natural Robustness Testing](https://mlsanity.com/paper/2402.11892/) (2024)
- [Investigating the Corruption Robustness of Image Classifiers with Random Lp-norm Corruptions](https://mlsanity.com/paper/2305.05400/) (2023)
- [Towards Virtual Clinical Trials of Radiology AI with Conditional Generative Modeling](https://mlsanity.com/paper/2502.09688/) (2025)
- [Does resistance to style-transfer equal Global Shape Bias? Measuring network sensitivity to global shape configuration](https://mlsanity.com/paper/2310.07555/) (2023)
- [A Bayesian Approach to OOD Robustness in Image Classification](https://mlsanity.com/paper/2403.07277/) (2024)
- [Achieving Domain-Independent Certified Robustness via Knowledge Continuity](https://mlsanity.com/paper/2411.01644/) (2024)
- [Aggregate Representation Measure for Predictive Model Reusability](https://mlsanity.com/paper/2405.09600/) (2024)
- [Transparency Distortion Robustness for SOTA Image Segmentation Tasks](https://mlsanity.com/paper/2405.12864/) (2024)
- [Causality-Driven Audits of Model Robustness](https://mlsanity.com/paper/2410.23494/) (2024)
- [MoENAS: Mixture-of-Expert based Neural Architecture Search for jointly Accurate, Fair, and Robust Edge Deep Neural Networks](https://mlsanity.com/paper/2502.07422/) (2025)

## Abstract (arXiv)

Deep neural networks for computer vision are deployed in increasingly safety-critical and socially-impactful applications, motivating the need to close the gap in model performance under varied, naturally occurring imaging conditions. Robustness, ambiguously used in multiple contexts including adversarial machine learning, refers here to preserving model performance under naturally-induced image corruptions or alterations. We perform a systematic review to identify, analyze, and summarize current definitions and progress towards non-adversarial robustness in deep learning for computer vision. We find this area of research has received disproportionately less attention relative to adversarial machine learning, yet a significant robustness gap exists that manifests in performance degradation similar in magnitude to adversarial conditions. Toward developing a more transparent definition of robustness, we provide a conceptual framework based on a structural causal model of the data generating process and interpret non-adversarial robustness as pertaining to a model's behavior on corrupted images corresponding to low-probability samples from the unaltered data distribution. We identify key architecture-, data augmentation-, and optimization tactics for improving neural network robustness. This robustness perspective reveals that common practices in the literature correspond to causal concepts. We offer perspectives on how future research may mind this evident and significant non-adversarial robustness gap.