# Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness

arXiv: https://arxiv.org/abs/2410.03030 · HTML: https://mlsanity.com/paper/2410.03030/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 61 of its 77 references that are in the map.
- First posted on arXiv 3 Oct 2024.

## Builds on (most cited first, 30 of 61)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [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)
- [On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima](https://mlsanity.com/paper/1609.04836/) (2016)
- [Linear Mode Connectivity and the Lottery Ticket Hypothesis](https://mlsanity.com/paper/1912.05671/) (2019)
- [Rigging the Lottery: Making All Tickets Winners](https://mlsanity.com/paper/1911.11134/) (2019)
- [Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science](https://mlsanity.com/paper/1707.04780/) (2017)
- [A Fourier Perspective on Model Robustness in Computer Vision](https://mlsanity.com/paper/1906.08988/) (2019)
- [Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data](https://mlsanity.com/paper/1808.01204/) (2018)
- [Comparing Rewinding and Fine-tuning in Neural Network Pruning](https://mlsanity.com/paper/2003.02389/) (2020)
- [Sparse Networks from Scratch: Faster Training without Losing Performance](https://mlsanity.com/paper/1907.04840/) (2019)
- [Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization](https://mlsanity.com/paper/1902.05967/) (2019)
- [Chasing Sparsity in Vision Transformers: An End-to-End Exploration](https://mlsanity.com/paper/2106.04533/) (2021)
- [Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch](https://mlsanity.com/paper/2102.04010/) (2021)
- [More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity](https://mlsanity.com/paper/2207.03620/) (2022)
- [Deep Rewiring: Training very sparse deep networks](https://mlsanity.com/paper/1711.05136/) (2017)
- [3D Common Corruptions and Data Augmentation](https://mlsanity.com/paper/2203.01441/) (2022)
- [Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training](https://mlsanity.com/paper/2102.02887/) (2021)
- [Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey](https://mlsanity.com/paper/1912.05170/) (2019)
- [On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness](https://mlsanity.com/paper/2102.11273/) (2021)
- [AugMax: Adversarial Composition of Random Augmentations for Robust Training](https://mlsanity.com/paper/2110.13771/) (2021)

## Built on by (most cited first, 11 of 11)

- [Leave it to the Specialist: Repair Sparse LLMs with Sparse Fine-Tuning via Sparsity Evolution](https://mlsanity.com/paper/2505.24037/) (2025)
- [Pushing the Limits of Sparsity: A Bag of Tricks for Extreme Pruning](https://mlsanity.com/paper/2411.13545/) (2024)
- [NeuroTrails: Training with Dynamic Sparse Heads as the Key to Effective Ensembling](https://mlsanity.com/paper/2505.17909/) (2025)
- [Addressing the Collaboration Dilemma in Low-Data Federated Learning via Transient Sparsity](https://mlsanity.com/paper/2506.00932/) (2025)
- [A Recovery Guarantee for Sparse Neural Networks](https://mlsanity.com/paper/2509.20323/) (2025)
- [Topology-Aware Revival for Efficient Sparse Training](https://mlsanity.com/paper/2602.04166/) (2026)
- [SparseOpt: Addressing Normalization-induced Gradient Skew in Sparse Training](https://mlsanity.com/paper/2605.27541/) (2026)
- [Memory-Efficient LLM Training with Dynamic Sparsity: From Stability to Practical Scaling](https://mlsanity.com/paper/2606.00888/) (2026)
- [Learning Subset-Shared Invariances for Domain Generalization with Mixture-of-Experts](https://mlsanity.com/paper/2606.25665/) (2026)
- [Robustness Emerges Early in Training Dynamics, but Is Not Preserved](https://mlsanity.com/paper/2608.04442/) (2026)
- [Suppress and Diversify: Refining Robust Pathways for Corruption Robustness](https://mlsanity.com/paper/2608.06712/) (2026)

## Abstract (arXiv)

It is generally perceived that Dynamic Sparse Training opens the door to a new era of scalability and efficiency for artificial neural networks at, perhaps, some costs in accuracy performance for the classification task. At the same time, Dense Training is widely accepted as being the "de facto" approach to train artificial neural networks if one would like to maximize their robustness against image corruption. In this paper, we question this general practice. Consequently, we claim that, contrary to what is commonly thought, the Dynamic Sparse Training methods can consistently outperform Dense Training in terms of robustness accuracy, particularly if the efficiency aspect is not considered as a main objective (i.e., sparsity levels between 10% and up to 50%), without adding (or even reducing) resource cost. We validate our claim on two types of data, images and videos, using several traditional and modern deep learning architectures for computer vision and three widely studied Dynamic Sparse Training algorithms. Our findings reveal a new yet-unknown benefit of Dynamic Sparse Training and open new possibilities in improving deep learning robustness beyond the current state of the art.