Accuracy: 32.2GFLOPS per prediction: 0.22
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
CSv1(%): 47.3CSv2(%): 71.1
CSv1(%): 45.43CSv2(%): 72.86
28 gestures accuracy: 99.9514 gestures accuracy: 99.85No. Parameters: 1.25
Accuracy: 30.9
28 gestures accuracy: 91.4314 gestures accuracy: 93.57
28 gestures accuracy: 95.3714 gestures accuracy: 97.74
CSv1(%): 36.97
CSv1(%): 47.96CSv2(%): 75.36
28 gestures accuracy: 94.314 gestures accuracy: 97.1No. Parameters: 1.75
28 gestures accuracy: 86.614 gestures accuracy: 91.3Speed (FPS): 361
CSv1(%): 43.0CSv2(%): 70.1
Accuracy: 98.3
CSv1(%): 29.90
CSv1(%): 37.98CSv2(%): 67.04
CSv1(%): 30.25CSv2(%): 56.14
28 gestures accuracy: 90.714 gestures accuracy: 93.6Speed (FPS): 161
CSv1(%): 34.84CSv2(%): 66.68
Accuracy: 87.8