4 accepted papers
Federated class-incremental learning (FCIL) aims to incrementally learn new classes across decentralized clients under non-IID data distributions. However, the pervasive challenge of label noise in FCIL has been completely overlooked. In this work, we introduce federated noisy class-incremental lear
With the rapid advancement of the digital economy, data collaboration between organizations has become a well-established business model, driving the growth of various industries. However, privacy concerns make direct data sharing impractical. To address this, Two-Party Split Learning (a.k.a. Verti…
The presence of haze negatively affects the visibility of captured images, posing challenges for general object detection models. We observe that current techniques exhibit three limitations: 1) they typically view image restoration and object detection as separate tasks; 2) they disregard potential…
Lightly-damped dynamics of a flexure-based mechanism will tend to largely deteriorate the broadband control performance if its hysteresis nonlinearity has been compensated. This paper developed a novel damped piezo-driven decoupled XYZ nanopositioning stage, which consists of three orthogonal parall…