.png){kind=icon}
Return
Dynamic deep multi-label image data augmentation based on self-paced learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.cviu.2025.104530.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• End-to-end framework improves multi-label classification via adaptive augmentation. • Self-paced learning selects easy samples to guide augmentation during training. • Image data synthesis reduces class imbalance in self-paced selected samples. • Noise-mitigation filters low-similarity samples to improve training quality.
Journal
IF:
3.5
Papers:
555
Citations:
7.3K
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSave
ShareSave
View more