multiple instance learning
A learning paradigm where labels are assigned to sets (bags) of instances rather than individual instances, useful for problems where annotations are difficult to obtain for all data points.
- Few-Shot Learning from Gigapixel Images via Hierarchical Vision-Language Alignment and Modeling
- Navigating the MIL Trade-Off: Flexible Pooling for Whole Slide Image Classification
- Revisiting End-to-End Learning with Slide-level Supervision in Computational Pathology
- Robust Hallucination Detection in LLMs via Adaptive Token Selection
- Sequential Attention-based Sampling for Histopathological Analysis
- Single GPU Task Adaptation of Pathology Foundation Models for Whole Slide Image Analysis