Robust Few-Shot Learning for User-Provided Data

IEEE Transactions on Neural Networks and Learning Systems, pp. 1433-1447, 2021.

Cited by: 0|Views85
WOS EI

Abstract:

Few-shot learning (FSL) focuses on distilling transferrable knowledge from existing experience to cope with novel concepts for which the labeled data are scarce. A typical assumption in FSL is that the training examples of novel classes are all clean with no outlier interference. In many realistic applications where examples are provided ...More

Code:

Data:

Your rating :
0

 

Tags
Comments