5 papers
Dynamic Visual-semantic Alignment for Zero-shot Learning with Ambiguous Labels
Jiangnan Li, Linqing Huang, Xiaowen Yan +3
Zero-shot learning (ZSL) aims to recognize unseen classes without visual instances. However, existing methods usually assume clean labels, overlooking real-world label noise and am…
Isospin-symmetry violation -- kaons and beyond (ISO-BREAK 25: summary and outlook)
Marek Gazdzicki, Francesco Giacosa, Katarzyna Grebieszkow +40
This report summarizes the presentations and discussions during the ISO-BREAK 25 Workshop ``Isospin symmetry violation: kaons and beyond'', which was held at Jan Kochanowski Univer…
CLIP-driven Zero-shot Learning with Ambiguous Labels
Jinfu Fan, Jiangnan Li, Xiaowen Yan +3
Zero-shot learning (ZSL) aims to recognize unseen classes by leveraging semantic information from seen classes, but most existing methods assume accurate class labels for training…
Diffusion Disambiguation Models for Partial Label Learning
Jinfu Fan, Xiaohui Zhong, Kangrui Ren +4
Learning from ambiguous labels is a long-standing problem in practical machine learning applications. The purpose of \emph{partial label learning} (PLL) is to identify the ground-t…
FedRS-Bench: Realistic Federated Learning Datasets and Benchmarks in Remote Sensing
Haodong Zhao, Peng Peng, Chiyu Chen +2
Remote sensing (RS) images are usually produced at an unprecedented scale, yet they are geographically and institutionally distributed, making centralized model training challengin…