.png){kind=icon}
.png){kind=icon}
Return
Learning semantic-aware threshold for multi-label image recognition with partial labels
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2025.129216.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
multi-label image recognition
partial labels
threshold learning
pseudo-labels
differential ranking loss
Journal
IF:
7.5
Papers:
2.9W
Citations:
10.2W