English

Modelling response to trypophobia trigger using intermediate layers of ImageNet networks

Computer Vision and Pattern Recognition 2020-02-27 v2

Abstract

In this paper, we approach the problem of detecting trypophobia triggers using Convolutional neural networks. We show that standard architectures such as VGG or ResNet are capable of recognizing trypophobia patterns. We also conduct experiments to analyze the nature of this phenomenon. To do that, we dissect the network decreasing the number of its layers and parameters. We prove, that even significantly reduced networks have accuracy above 91% and focus their attention on the trypophobia patterns as presented on the visual explanations.

Keywords

Cite

@article{arxiv.2002.08490,
  title  = {Modelling response to trypophobia trigger using intermediate layers of ImageNet networks},
  author = {Piotr Woźnicki and Michał Kuźba and Piotr Migdał},
  journal= {arXiv preprint arXiv:2002.08490},
  year   = {2020}
}

Comments

extended abstract submitted to Eastern European Machine Learning 2019, 3 pages, 2 figures, 1 table

R2 v1 2026-06-23T13:47:30.715Z