Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision

09/16/2021
by   David Picard, et al.
29

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/09/2019

GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing

We present GluonCV and GluonNLP, the deep learning toolkits for computer...
research
02/19/2023

A Comprehensive Evaluation Study on Risk Level Classification of Melanoma by Computer Vision on ISIC 2016-2020 Datasets

Skin cancer is the most common type of cancer. Specifically, melanoma is...
research
06/06/2021

Exploring the Limits of Out-of-Distribution Detection

Near out-of-distribution detection (OOD) is a major challenge for deep n...
research
02/03/2021

Deep CNNs for large scale species classification

Large Scale image classification is a challenging problem within the fie...
research
10/08/2021

Inferring Offensiveness In Images From Natural Language Supervision

Probing or fine-tuning (large-scale) pre-trained models results in state...
research
12/07/2020

GenScan: A Generative Method for Populating Parametric 3D Scan Datasets

The availability of rich 3D datasets corresponding to the geometrical co...
research
06/24/2020

Large image datasets: A pyrrhic win for computer vision?

In this paper we investigate problematic practices and consequences of l...

Please sign up or login with your details

Forgot password? Click here to reset