OwMatch: Conditional Self-Labeling with Consistency for Open-World Semi-Supervised Learning
–Neural Information Processing Systems
Semi-supervised learning (SSL) offers a robust framework for harnessing the potential of unannotated data. Traditionally, SSL mandates that all classes possess labeled instances.
Neural Information Processing Systems
Feb-17-2026, 15:19:20 GMT
- Country:
- Asia > China
- Guangdong Province > Shenzhen (0.04)
- Hong Kong (0.04)
- Asia > China
- Genre:
- Research Report > Experimental Study (0.93)
- Technology: