AI Chat AI Image Generator AI Video Text to Speech

Self Meta Pseudo Labels: Meta Pseudo Labels Without The Teacher

12/27/2022

∙

by Kei-Sing Ng, et al.

∙

∙

We present Self Meta Pseudo Labels, a novel semi-supervised learning method similar to Meta Pseudo Labels but without the teacher model. We introduce a novel way to use a single model for both generating pseudo labels and classification, allowing us to store only one model in memory instead of two. Our method attains similar performance to the Meta Pseudo Labels method while drastically reducing memory usage.

Kei-Sing Ng
1 publication
Qingchen Wang
2 publications

research

∙ 10/12/2021

Couple Learning: Mean Teacher method with pseudo-labels improves semi-supervised deep learning results

The recently proposed Mean Teacher has achieved state-of-the-art results...

0 Rui Tao, et al. ∙

research

∙ 05/15/2022

Meta Self-Refinement for Robust Learning with Weak Supervision

Training deep neural networks (DNNs) with weak supervision has been a ho...

0 Dawei Zhu, et al. ∙

research

∙ 03/22/2022

Pseudo Label Is Better Than Human Label

State-of-the-art automatic speech recognition (ASR) systems are trained ...

0 Dongseong Hwang, et al. ∙

research

∙ 05/30/2022

Conformal Credal Self-Supervised Learning

In semi-supervised learning, the paradigm of self-training refers to the...

19 Julian Lienen, et al. ∙

research

∙ 07/09/2022

Generating Pseudo-labels Adaptively for Few-shot Model-Agnostic Meta-Learning

Model-Agnostic Meta-Learning (MAML) is a famous few-shot learning method...

0 Guodong Liu, et al. ∙

research

∙ 03/23/2020

Meta Pseudo Labels

Many training algorithms of a deep neural network can be interpreted as ...

0 Hieu Pham, et al. ∙

research

∙ 10/15/2020

Unsupervised Self-training Algorithm Based on Deep Learning for Optical Aerial Images Change Detection

Optical aerial images change detection is an important task in earth obs...

9 Yuan Zhou, et al. ∙