Meta Pseudo Labels is a semi-supervised learning method that uses a teacher network to generate pseudo labels on unlabeled data to teach a student network. The teacher receives feedback from the student to inform the teacher to generate better pseudo labels. This feedback signal is used as a reward to train the teacher throughout the course of the student’s learning.
Source: Meta Pseudo LabelsPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Semi-Supervised Image Classification | 3 | 30.00% |
Image Classification | 2 | 20.00% |
Fine-Grained Image Classification | 1 | 10.00% |
Image Manipulation | 1 | 10.00% |
Interspecies Facial Keypoint Transfer | 1 | 10.00% |
Keypoint Detection | 1 | 10.00% |
Meta-Learning | 1 | 10.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |