[2109.08203] Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision
Abstract:In this paper I investigate the effect of random seed selection on the accuracy when using popular deep learning architectures for computer vision. I scan a large amount of seeds (up to $10^4$) on CIFAR 10 and I also scan fewer seeds on Imagenet using pre-trained models to investigate large scale datasets. The conclusions are that even if the variance is not very large, it is surprisingly easy to find an outlier that performs much better or much worse than the average.
View PDF HTML (experimental) Abstract:In this paper I investigate the effect of random seed selection on the accuracy when using popular deep learning architectures for computer vision. I scan a large amount of seeds (up to $10^4$) on CIFAR 10 and I also scan fewer seeds on Imagenet using pre-trained models to investigate large scale datasets. The conclusions are that even if the variance is not very large, it is surprisingly easy to find an outlier that performs much better or much worse than the average. Comments: fixed typos Subjects: Computer Vision and Pattern Recognition (cs.CV)…
saved by
related reading
- How our data shaped neural architecture discovery, and how automation can reshape the future | Core Automationcoreauto.com
- [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
- Understanding deep learning requires rethinking generalizationarxiv.org
- [2203.09795] Three things everyone should know about Vision Transformersarxiv.org
- Deep Anomaly Detection with Outlier Exposurearxiv.org
- arxiv.org/pdf/1805.08522arxiv.org
- [1706.04599] On Calibration of Modern Neural Networksarxiv.org
- [1810.13128] The Effect of Learning Strategy versus Inherent Architecture Properties on the Ability of Convolutional Neural Networks to Develop Transformation Invariancearxiv.org
- ImageNet Classification with Deep Convolutional Neural Networksproceedings.neurips.cc
- https://arxiv.org/pdf/2006.11239arxiv.org
- [1709.06560] Deep Reinforcement Learning that Mattersarxiv.org
- Your Out-of-Distribution Detection Method is Not Robust!arxiv.org