Accuracy: 36.9GFLOPS per prediction: 26.91
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: 49.1
Accuracy: 37.8
Accuracy: 50.3
Accuracy: 34.8
Accuracy: 33.5
Accuracy: 38.0
Accuracy: 37.9
Accuracy: 40.9
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching
Accuracy: 37.1
Accuracy: 38.4
Accuracy: 33.7
Accuracy: 34.8
Accuracy: 51.9
Accuracy: 37.4
Accuracy: 36.9
Accuracy: 36.6
Accuracy: 33.6
Accuracy: 38.6
Accuracy: 37.5