zero shot learning

Zero-shot learning (ZSL) is a problem setup in machine learning where, at test time, a learner observes samples from classes which were not observed during training, and needs to predict the class that they belong to. 1 It works by using contrastive learning to minimize the difference between the encodings of the image and its corresponding text, and then combining the two techniques to make predictions. 2 Zero-shot learning is a machine learning method that allows a model to recognize what it hasn't seen before, allowing it to classify classes that it hasn't seen before. 2 Zero-Shot Learning (ZSL) is a Machine Learning paradigm where a pre-trained deep learning model is made to generalize on a novel category of samples, i.e., the training and testing set classes are disjoint. 3