Learning Semantic-Aware Threshold for Multi-Label Image Recognition with Partial Labels
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916872639741952 |
|---|---|
| author | Ruan, Haoxian Xu, Zhihua Yang, Zhijing Ma, Guang Xie, Jieming Fan, Changxiang Chen, Tianshui |
| author_facet | Ruan, Haoxian Xu, Zhihua Yang, Zhijing Ma, Guang Xie, Jieming Fan, Changxiang Chen, Tianshui |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_23263 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Semantic-Aware Threshold for Multi-Label Image Recognition with Partial Labels Ruan, Haoxian Xu, Zhihua Yang, Zhijing Ma, Guang Xie, Jieming Fan, Changxiang Chen, Tianshui Computer Vision and Pattern Recognition 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. |
| title | Learning Semantic-Aware Threshold for Multi-Label Image Recognition with Partial Labels |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.23263 |