Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learning

TL;DR

This paper introduces a dual-decoupling learning approach combined with metric-adaptive thresholding to enhance pseudo-label quality in semi-supervised multi-label learning, leading to state-of-the-art results.

Contribution

It proposes a novel dual-decoupling method for better feature learning and a metric-adaptive thresholding strategy for optimal pseudo-labeling in SSMLL.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Significantly outperforms existing methods in pseudo-label accuracy.

Improves the robustness of semi-supervised multi-label learning.

Abstract

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.