arXiv · Artificial Intelligence· Nguyen Ho, Bach Tung Tran, Trung Ky Nguyen, Zhenchang Xia, Bolong Zheng, Long Van Ho·· 16 小时前AI 评分25
双流 OSSE-LSTM 与反事实归因实现大规模少标签时间序列分类
Label-Efficient Time Series Classification at Scale: A Dual-Stream OSSE-LSTM with Counterfactual Attribution
AI 导读
论文提出 Dual-Stream OSSE-LSTM，一种 episodic metric-learning 框架，将 Omni-Scale CNN 与 Squeeze-and-Excitation 重校准和双向 LSTM 融合为 prototype-oriented embedding。
来源：arXiv · Artificial Intelligence · arxiv.org