contrastive learning
PulseAugur coverage of contrastive learning — every cluster mentioning contrastive learning across labs, papers, and developer communities, ranked by signal.
-
PEARL框架利用对比学习改进直播推荐
研究人员开发了PEARL，一个用于大规模直播推荐系统中无偏百分位数估计的新框架。该方法使用对比学习来模拟用户的相对偏好，避免了用户活跃度差异带来的偏差。在一个主要的直播平台上进行的在线A/B测试显示了显著的改进，包括观看时长增加了2.10%，互动率上升了1.49%。
-
Vol-Mark introduces reversible watermarking for 3D medical data
Researchers have developed Vol-Mark, a novel reversible watermarking technique designed to protect the ownership and authenticity of 3D medical volume data. This method utilizes contrastive learning to extract robust vo…
-
New research explores dataset poisoning for AI watermarking and IP protection
This research paper explores the feasibility of using dataset poisoning techniques as a method for watermarking contrastive learning datasets. The study reveals that existing data-poisoning attacks have limitations in a…
-
综述文章回顾了用于跨主题脑电图解码挑战的深度学习方法
本综述文章回顾了旨在提高脑电图（EEG）解码在不同受试者之间泛化能力的深度学习技术。文章讨论了高受试者间变异性带来的挑战，这种变异性会在训练数据和测试数据之间产生领域迁移。文章将现有方法分为特征对齐、对抗学习、特征解耦和对比学习等几类，并讨论了理论局限性和脑电图基础模型的潜力。