Contrastive Label Enhancement
This work addresses label ambiguity in machine learning, offering a novel approach for label enhancement that could improve tasks like multi-label classification, though it appears incremental as it builds on existing label distribution learning methods.
The paper tackles the problem of recovering label distributions from logical labels in label distribution learning by proposing Contrastive Label Enhancement (ConLE), which integrates features and logical labels into a unified projection space using contrastive learning, and experiments on benchmark datasets show its effectiveness and superiority.
Label distribution learning (LDL) is a new machine learning paradigm for solving label ambiguity. Since it is difficult to directly obtain label distributions, many studies are focusing on how to recover label distributions from logical labels, dubbed label enhancement (LE). Existing LE methods estimate label distributions by simply building a mapping relationship between features and label distributions under the supervision of logical labels. They typically overlook the fact that both features and logical labels are descriptions of the instance from different views. Therefore, we propose a novel method called Contrastive Label Enhancement (ConLE) which integrates features and logical labels into the unified projection space to generate high-level features by contrastive learning strategy. In this approach, features and logical labels belonging to the same sample are pulled closer, while those of different samples are projected farther away from each other in the projection space. Subsequently, we leverage the obtained high-level features to gain label distributions through a welldesigned training strategy that considers the consistency of label attributes. Extensive experiments on LDL benchmark datasets demonstrate the effectiveness and superiority of our method.