Listen to this story
Computational: We take random inputs, follow complex steps, and hope the output makes sense. And then blog about it.
Part of HackerNoon's growing list of open-source research papers, promoting free access to academic material.
Authors:
(1) Athanasios Angelakis, Amsterdam University Medical Center, University of Amsterdam - Data Science Center, Amsterdam Public Health Research Institute, Amsterdam, Netherlands
(2) Andrey Rass, Den Haag, Netherlands.
[32x32, 31x31, 30x30,
29x29, 28x28, 27x27,
26x26, 25x25, 24x24,
22x22, 21x21, 20x20,
19x19, 18x18, 17x17,
16x16, 15x15, 14x14,
13x13, 12x12, 11x11,
10x10, 9x9, 8x8,
6x6,5x5, 4x4, 3x3]
(a) The results in all figures employ official ResNet50 models from Tensorflow trained from scratch on the CIFAR-100 dataset with random crop data augmentation applied. All results in this figure are averaged over 4 runs. During training, the proportion of the original image obscured by the augmentation varies from 100% to 10%. We observe The vertical dotted lines denote the best test accuracy for every class.
(a) The results in all figures employ official ResNet50 models from Tensorflow trained from scratch on the CIFAR-100 dataset with random crop and random horizontal flip data augmentations applied. All results in this figure are averaged over 4 runs. During training, the proportion of the original image obscured by the augmentation varies from 100% to 10%. We observe The vertical dotted lines denote the best test accuracy for every class.
Without Random Horizontal Flip:
With Random Horizontal Flip
This paper is available on arxiv under CC BY 4.0 DEED license.