Learning Semantic-Aware Threshold for Multi-Label Image Recognition with Partial Labels
This addresses the challenge of training models with incomplete labels in multi-label image recognition, offering a novel solution for scenarios with limited labeled data.
The paper tackles the problem of multi-label image recognition with partial labels by introducing the Semantic-Aware Threshold Learning (SATL) algorithm, which dynamically learns category-specific thresholds and improves performance, achieving significant gains on datasets like Microsoft COCO and VG-200.
Multi-label image recognition with partial labels (MLR-PL) is designed to train models using a mix of known and unknown labels. Traditional methods rely on semantic or feature correlations to create pseudo-labels for unidentified labels using pre-set thresholds. This approach often overlooks the varying score distributions across categories, resulting in inaccurate and incomplete pseudo-labels, thereby affecting performance. In our study, we introduce the Semantic-Aware Threshold Learning (SATL) algorithm. This innovative approach calculates the score distribution for both positive and negative samples within each category and determines category-specific thresholds based on these distributions. These distributions and thresholds are dynamically updated throughout the learning process. Additionally, we implement a differential ranking loss to establish a significant gap between the score distributions of positive and negative samples, enhancing the discrimination of the thresholds. Comprehensive experiments and analysis on large-scale multi-label datasets, such as Microsoft COCO and VG-200, demonstrate that our method significantly improves performance in scenarios with limited labels.