Results for "few labels"
Self-Supervised Learning
Intermediate
Learning from data by constructing “pseudo-labels” (e.g., next-token prediction, masked modeling) without manual annotation.
Bias
Intermediate
Systematic differences in model outcomes across groups; arises from data, labels, and deployment context.
Segmentation
Intermediate
Assigning labels per pixel (semantic) or per instance (instance segmentation) to map object boundaries.
Image Classification
Intermediate
Assigning category labels to images.
Few-Shot Learning
Intermediate
Achieving task performance by providing a small number of examples inside the prompt without weight updates.
Few-Shot Prompting
Intro
Multiple examples included in prompt.