297 papers with code • 16 benchmarks • 24 datasets
Zero-shot learning (ZSL) is a model's ability to detect classes never seen during training. The condition is that the classes are not known during supervised learning.
Earlier work in zero-shot learning use attributes in a two-step approach to infer unknown classes. In the computer vision context, more recent advances learn mappings from image feature space to semantic space. Other approaches learn non-linear multimodal embeddings. In the modern NLP context, language models can be evaluated on downstream tasks without fine tuning.
( Image credit: Prototypical Networks for Few shot Learning in PyTorch )
Once trained, a RN is able to classify images of new classes by computing relation scores between query images and the few examples of each new class without further updating the network.
State-of-the-art methods for zero-shot visual recognition formulate learning as a joint embedding problem of images and side information.
Due to the importance of zero-shot learning, i. e. classifying images where there is a lack of labeled training data, the number of proposed approaches has recently increased steadily.
The zero-shot paradigm exploits vector-based word representations extracted from text corpora with unsupervised methods to learn general mapping functions from other feature spaces onto word space, where the words associated to the nearest neighbours of the mapped vectors are used as their linguistic labels.