Partial label learning is a weakly supervised learn- ing framework, in which each instance is provid- ed with multiple candidate labels while only one of them ...

Partial label learning is a weakly supervised learning framework, in which each instance is provided with multiple candidate labels while only one of them ...

This paper proposes a novel approach that aims to maximize the latent semantic differences of the two instances whose groundtruth labels are definitely ...

We propose a novel approach that aims to maximize the latent semantic differences of the two instances whose groundtruth labels are definitely different.

We showcase our approach by using the ParSE [10] method. ParSE based on learning visual-semantic representations, introduces a novel weighted calibration rank ...

Sep 13, 2024 · Partial/complementary label learning is an emerging framework in weakly supervised machine learning with broad application prospects. It handles ...

Aug 14, 2022 · The core of PLL is to learn efficient feature representations to facilitate label disambiguation. However, existing PLL methods only learn plain ...

This paper begins with a research on the label correlation, followed by the establishment of a unified framework that integrates the label correlation.

This method can capture the semantic clusters with the most unique information in the latent space and automatically adapt to different feature distributions.

Feng and An (2019) developed a PLL algorithm by using semantic difference maximization. Lyu et al. (2020) proposed a self-paced PLL algorithm. Yao et al. (2020a ...