Improving adversarially robust few-shot image classification with generalizable representations
Abstract Few-Shot Image Classification (FSIC) aims to recognize novel image classes with
limited data, which is significant in practice. In this paper, we consider the FSIC problem in …
limited data, which is significant in practice. In this paper, we consider the FSIC problem in …
Latent feature relation consistency for adversarial robustness
Deep neural networks have been applied in many computer vision tasks and achieved state-
of-the-art performance. However, misclassification will occur when DNN predicts adversarial …
of-the-art performance. However, misclassification will occur when DNN predicts adversarial …
A Survey on Bias Mitigation in Federated Learning
Federated learning (FL) enables collaborative model training while keeping data
decentralized. However, system heterogeneity and statistical differences in decentralized …
decentralized. However, system heterogeneity and statistical differences in decentralized …
Generalizable and Discriminative Representations for Adversarially Robust Few-Shot Learning
Few-shot image classification (FSIC) is beneficial for a variety of real-world scenarios,
aiming to construct a recognition system with limited training data. In this article, we extend …
aiming to construct a recognition system with limited training data. In this article, we extend …
[PDF][PDF] 针对未知攻击的泛化性对抗防御技术综述
周大为， 徐一搏， 王楠楠， 刘德成， 彭春蕾， 高新波 - 中国图象图形学报 - cjig.cn
在计算机视觉领域, 对抗样本是一种包含攻击者所精心设计的扰动的样本,
该样本与其对应的自然样本的差异通常难以被人眼察觉, 却极易导致深度学习模型输出错误结果 …
该样本与其对应的自然样本的差异通常难以被人眼察觉, 却极易导致深度学习模型输出错误结果 …