
提案されたTSFoolアプローチは、RNNベースの時系列分類における高度に認識しにくい敵対的な時系列を効率的に作成し、既存の手法を効果、効率、認識性の観点で大幅に上回っています。


coremsg

tsfool-crafting-highly-imperceptible-adversarial-time-series-through-multi-objective-attack


TSFool: Crafting Highly-Imperceptible Adversarial Time Series through Multi-Objective Attack


title_rewrite


CrossTimeNet proposes a novel cross-domain SSL learning framework to enhance time series representation through self-supervised pre-training, achieving superior performance in various domains.


learning-transferable-time-series-classifier-with-cross-domain-pre-training-from-language-model


Learning Transferable Time Series Classifier with Cross-Domain Pre-training from Language Model



The author introduces pre-trained domain foundation models to address overfitting in Time Series Classification, demonstrating superior performance compared to traditional methods.


Unveiling-Foundation-Models-for-Time-Series-Classification-with-a-PreText-Task


Unveiling Foundation Models for Time Series Classification with a PreText Task
