Accuracy: 99.2
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
Accuracy: 97.3
Accuracy: 92.3%
Accuracy: 95.69Data Modality (Joint, Bone, Motion): Joint
Accuracy: 96.34%Data Modality (Joint, Bone, Motion): Joint
Accuracy: 96.5
Accuracy: 98.5%
Accuracy: 96.98
Accuracy: 90.7%
Accuracy: 97.2
Accuracy: 87.6%
Accuracy: 96%
Accuracy: 93.99
Accuracy: 97.2
Accuracy: 97.1%
Accuracy: 97.0
Accuracy: 96.7
Accuracy: 97.6
Accuracy: 93.7
Accuracy: 97.5
Accuracy: 95.3
Accuracy: 98.5%
Accuracy: 92.5%
Accuracy: 97.0
Accuracy: 99.50%
Accuracy: 97.4
Accuracy: 88.1%
Accuracy: 93.5
Accuracy: 93.5