Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learning
This work addresses the problem of reducing annotation costs in multi-label learning for researchers and practitioners, presenting an incremental improvement over existing thresholding methods.
The paper tackles the challenge of generating accurate pseudo-labels in semi-supervised multi-label learning by proposing a dual-decoupling method to improve prediction quality and a metric-adaptive thresholding strategy to optimize thresholds, achieving state-of-the-art performance on benchmark datasets.
Semi-supervised multi-label learning (SSMLL) is a powerful framework for leveraging unlabeled data to reduce the expensive cost of collecting precise multi-label annotations. Unlike semi-supervised learning, one cannot select the most probable label as the pseudo-label in SSMLL due to multiple semantics contained in an instance. To solve this problem, the mainstream method developed an effective thresholding strategy to generate accurate pseudo-labels. Unfortunately, the method neglected the quality of model predictions and its potential impact on pseudo-labeling performance. In this paper, we propose a dual-perspective method to generate high-quality pseudo-labels. To improve the quality of model predictions, we perform dual-decoupling to boost the learning of correlative and discriminative features, while refining the generation and utilization of pseudo-labels. To obtain proper class-wise thresholds, we propose the metric-adaptive thresholding strategy to estimate the thresholds, which maximize the pseudo-label performance for a given metric on labeled data. Experiments on multiple benchmark datasets show the proposed method can achieve the state-of-the-art performance and outperform the comparative methods with a significant margin.