CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning

arXiv:2303.10365v3 Announce Type: replace
Abstract: Partial-label learning (PLL) is an important weakly supervised learning problem, which allows each training example to have a candidate label set instead of a single ground-truth label. Identification-based methods have been widely explored to tackle label ambiguity issues in PLL, which regard the true label as a latent variable to be identified. However, identifying the true labels accurately and completely remains challenging, causing noise in pseudo labels during model training. In this paper, we propose …

abstract arxiv cs.ai cs.lg example ground-truth identification labels regard set supervised learning training true truth type