Investigating the Impact of Randomness on Reproducibility in Computer Vision: A Study on Applications in Civil Engineering and Medicine
Not on the map. Why?
Abstract (arXiv)
Reproducibility is essential for scientific research. However, in computer vision, achieving consistent results is challenging due to various factors. One influential, yet often unrecognized, factor is CUDA-induced randomness. Despite CUDA's advantages for accelerating algorithm execution on GPUs, if not controlled, its behavior across multiple executions remains non-deterministic. While reproducibility issues in ML being researched, the implications of CUDA-induced randomness in application are yet to be understood. Our investigation focuses on this randomness across one standard benchmark dataset and two real-world datasets in an isolated environment. Our results show that CUDA-induced randomness can account for differences up to 4.77% in performance scores. We find that managing this variability for reproducibility may entail increased runtime or reduce performance, but that disadvantages are not as significant as reported in previous studies.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 15 of its 41 references that are in the map. First posted on arXiv 19 Sep 2024.
Builds on
15 of 41 references.
References · 15
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
- 2019Quantifying the Carbon Emissions of Machine Learningcited by 516
- 2020Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)cited by 318
- 2017The Marginal Value of Adaptive Gradient Methods in Machine Learningcited by 248
- 2020The Hardware Lotterycited by 160
- 2020An Improved Analysis of Stochastic Gradient Descent with Momentumcited by 117
- 2021Randomness In Neural Network Training: Characterizing The Impact of Toolingcited by 57
- 2020An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localizationcited by 43
- 2022Towards Training Reproducible Deep Learning Modelscited by 23
- 2019Globally-Aware Multiple Instance Classifier for Breast Cancer Screeningcited by 12
- 2021Synthesizing Irreproducibility in Deep Networkscited by 9
3 more
- 2022Experimental Standards for Deep Learning in Natural Language Processing Researchcited by 9
- 2022Quantifying Inherent Randomness in Machine Learning Algorithmscited by 6
- 2022Towards a trustworthy, secure and reliable enclave for machine learning in a hospital setting: The Essen Medical Computing Platform (EMCP)cited by 1
Built on by
Citing papers per year: 2026: 2.
2 papers.