Modelling response to trypophobia trigger using intermediate layers of ImageNet networks

2020/02/19 by Piotr Woźnicki, Woźnicki, Piotr, Michał Kuźba +3
Computer Science · #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #Currency Recognition and Detection #Digital Media Forensic Detection #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.2002.08490

openalex publication_date 2020/02/19 · openalex created_date 2020/03/06 · openalex updated_date 2026/07/28

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.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Gradient-based learning applied to document recognition

Related

• Is Attentional Channel Processing Design Required? Comprehensive Analysis Of Robustness Between Vision Transformers And Fully Attentional Networks
• White Noise Analysis of Neural Networks
• Out of the Black Box: Properties of deep neural networks and their applications
• Why Do Deep Neural Networks Still Not Recognize These Images?: A Qualitative Analysis on Failure Cases of ImageNet Classification
• Towards Robust Image Classification Using Sequential Attention Models