AUC: 0.613f-Score: 0.199Intersection over Union: 0.125
Papers with Code · CC BY-SA 4.0
Zero-Shot Learning
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.
Benchmark datasets for zero-shot learning include aPY, AwA, and CUB, among others.
( Image credit: Prototypical Networks for Few shot Learning in PyTorch )
Further readings:
논문
AUC: 0.769
AUC: .966Balanced Accuracy: .935
AUC: 0.542f-Score: 0.165Intersection over Union: 0.100
AUC: 0.858f-Score: 0.466Intersection over Union: 0.421
AUC: .576Balanced Accuracy: .289
AUC: .552Balanced Accuracy: .358
AUC: .747Balanced Accuracy: .525
AUC: .669Balanced Accuracy: .233
AUC: .984Balanced Accuracy: .930