Aug 2026
MD2PLL: a meta-learning framework for robust disambiguation in partial-label visual recognition
A meta-learning-based dual-model disambiguation for partial-label learning (MD2PLL), a robust framework for candidate-label disambiguation under ambiguous annotations, is proposed and achieves competitive performance on Yahoo! News and Soccer Player.
Xiaohui Zhong, Xiaowen Yan, Jiayin Song et al.
· The Visual Computer · 0 citations