Learning from Reduced Labels for Long-Tailed Data
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915044875304960 |
|---|---|
| author | Wei, Meng Li, Zhongnian Zhou, Yong Xu, Xinzheng |
| author_facet | Wei, Meng Li, Zhongnian Zhou, Yong Xu, Xinzheng |
| contents | Long-tailed data is prevalent in real-world classification tasks and heavily relies on supervised information, which makes the annotation process exceptionally labor-intensive and time-consuming. Unfortunately, despite being a common approach to mitigate labeling costs, existing weakly supervised learning methods struggle to adequately preserve supervised information for tail samples, resulting in a decline in accuracy for the tail classes. To alleviate this problem, we introduce a novel weakly supervised labeling setting called Reduced Label. The proposed labeling setting not only avoids the decline of supervised information for the tail samples, but also decreases the labeling costs associated with long-tailed data. Additionally, we propose an straightforward and highly efficient unbiased framework with strong theoretical guarantees to learn from these Reduced Labels. Extensive experiments conducted on benchmark datasets including ImageNet validate the effectiveness of our approach, surpassing the performance of state-of-the-art weakly supervised methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_16469 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning from Reduced Labels for Long-Tailed Data Wei, Meng Li, Zhongnian Zhou, Yong Xu, Xinzheng Machine Learning Computer Vision and Pattern Recognition Long-tailed data is prevalent in real-world classification tasks and heavily relies on supervised information, which makes the annotation process exceptionally labor-intensive and time-consuming. Unfortunately, despite being a common approach to mitigate labeling costs, existing weakly supervised learning methods struggle to adequately preserve supervised information for tail samples, resulting in a decline in accuracy for the tail classes. To alleviate this problem, we introduce a novel weakly supervised labeling setting called Reduced Label. The proposed labeling setting not only avoids the decline of supervised information for the tail samples, but also decreases the labeling costs associated with long-tailed data. Additionally, we propose an straightforward and highly efficient unbiased framework with strong theoretical guarantees to learn from these Reduced Labels. Extensive experiments conducted on benchmark datasets including ImageNet validate the effectiveness of our approach, surpassing the performance of state-of-the-art weakly supervised methods. |
| title | Learning from Reduced Labels for Long-Tailed Data |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.16469 |