Showing cs.CVShow all
3 papers · 1 filter
cs.CV2023
A Fine-Grained Image Description Generation Method Based on Joint Objectives
Yifan Zhang, Chunzhen Lin, Donglin Cao +1
The goal of fine-grained image description generation techniques is to learn detailed information from images and simulate human-like descriptions that provide coherent and compreh…
cs.CV2023
Comparative Evaluation of Recent Universal Adversarial Perturbations in Image Classification
Juanjuan Weng, Zhiming Luo, Dazhen Lin +1
The vulnerability of Convolutional Neural Networks (CNNs) to adversarial samples has recently garnered significant attention in the machine learning community. Furthermore, recent…
cs.CV2023
Boosting Adversarial Transferability via Fusing Logits of Top-1 Decomposed Feature
Juanjuan Weng, Zhiming Luo, Dazhen Lin +2
Recent research has shown that Deep Neural Networks (DNNs) are highly vulnerable to adversarial samples, which are highly transferable and can be used to attack other unknown black…