Zero-Shot

[Paper Exploration] In-Depth Analysis of the Segment Anything Model (SAM)

A comprehensive exploration of Meta AI's Segment Anything Model (SAM), a foundation model designed to generalize across various segmentation tasks with minimal prompting, zero-shot and few-shot learning capabilities, and applications in a wide range of domains.

sota zero shot few shot machine learning deep learning sam computer vision image segmentation meta ai
Zero-Shot

[Paper Exploration] Train Once, Test Anywhere: Zero-Shot Learning for Text Classification

A machine learning paradigm where a model is trained on certain tasks and then applied to new, unseen tasks without additional training. It leverages generalizable knowledge to perform well on tasks it has not explicitly encountered during training. (an instance og transfer learning)

classification nlp zero-shot