Adversarial Examples for Image Cropping: Gradient-Based and Bayesian-Optimized Approaches for Effective Adversarial Attack

In this study, we propose novel approaches for generating adversarial examples targeting machine learning-based image cropping systems. Image cropping is crucial for meeting display space restrictions and highlighting content’s interest areas. However, existing image cropping systems often mi...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Masatomo Yoshida, Haruto Namura, Masahiro Okuda
Format:	Artigo
Sprog:	Inglês
Udgivet:	IEEE 2024-01-01
Serier:	IEEE Access
Fag:	Adversarial examples image cropping object detection saliency map Twitter
Online adgang:	https://ieeexplore.ieee.org/document/10559590/
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!