Zero-shot learning (ZSL) is a machine learning approach that enables models to recognize and classify objects or concepts they have never encountered during training. This capability is achieved by leveraging auxiliary information, such as semantic attributes or textual descriptions, which relate unseen classes to those the model has already learned. For instance, a model trained to identify various animals can recognize a zebra by understanding that it shares attributes with horses but has distinctive black-and-white stripes.
In practice, zero-shot learning is particularly valuable in scenarios where obtaining labeled data for every possible class is impractical. By utilizing descriptive information, models can generalize to new classes without explicit examples. This approach has been successfully applied in fields like computer vision, natural language processing, and computational biology.
« Back to Glossary Index