HM: 19.67ZSL: 14.00
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
HM: 10.71ZSL: 7.91
HM: 12.13ZSL: 9.13
HM: 12.65ZSL: 9.50
HM: 7.27ZSL: 6.34
HM: 6.44ZSL: 5.40
HM: 5.12ZSL: 5.84
mAP: 15.1
mAP: 67.10