weakly supervised learning
Weakly supervised learning involves training models with partially labeled data or noisy labels. This approach aims to leverage abundant unlabeled data while minimizing reliance on high-quality labels, expanding the applicability of supervised learning.
- Bridging Sign and Spoken Languages: Pseudo Gloss Generation for Sign Language Translation
- Can Class-Priors Help Single-Positive Multi-Label Learning?
- Few-Shot Learning from Gigapixel Images via Hierarchical Vision-Language Alignment and Modeling
- Guiding LLM Decision-Making with Fairness Reward Models
- Imbalances in Neurosymbolic Learning: Characterization and Mitigating Strategies
- PC-Net: Weakly Supervised Compositional Moment Retrieval via Proposal-Centric Network
- PUATE: Efficient ATE Estimation from Treated (Positive) and Unlabeled Units