Improving Robustness to out-of-Distribution Data by Frequency-Based Augmentation

Although Convolutional Neural Networks (CNNs) have high accuracy in image recognition, they are vulnerable to adversarial examples and out-of-distribution data, and the difference from human recognition has been pointed out. In order to improve the robustness against out-of-distribution data, we pre...

Full description

Saved in:
Bibliographic Details
Main Authors: Mukai, Koki, Kumano, Soichiro, Yamasaki, Toshihiko
Format: Conference Proceeding
Language:English
Subjects:
Convolutional neural networks
data augmentation
Data models
frequency
Image recognition
neural network
out-of-distribution
Receivers
Robustness
Training data
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Although Convolutional Neural Networks (CNNs) have high accuracy in image recognition, they are vulnerable to adversarial examples and out-of-distribution data, and the difference from human recognition has been pointed out. In order to improve the robustness against out-of-distribution data, we present a frequency-based data augmentation technique that replaces the frequency components with other images of the same class. When the training data are CIFAR10 and the out-of-distribution data are SVHN, the Area Under Receiver Operating Characteristic (AUROC) curve of the model trained with the proposed method increases from 89.22% to 98.15%, and further increased to 98.59% when combined with another data augmentation method. Furthermore, we experimentally demonstrate that the robust model for out-of-distribution data uses a lot of high-frequency components of the image.
ISSN:2381-8549
DOI:10.1109/ICIP46576.2022.9897504