RealMix: Towards Realistic Semi-Supervised Deep Learning Algorithms

12/18/2019
by   Varun Nair, et al.
0

Semi-Supervised Learning (SSL) algorithms have shown great potential in training regimes when access to labeled data is scarce but access to unlabeled data is plentiful. However, our experiments illustrate several shortcomings that prior SSL algorithms suffer from. In particular, poor performance when unlabeled and labeled data distributions differ. To address these observations, we develop RealMix, which achieves state-of-the-art results on standard benchmark datasets across different labeled and unlabeled set sizes while overcoming the aforementioned challenges. Notably, RealMix achieves an error rate of 9.79 to surpass baseline performance when there is significant mismatch in the labeled and unlabeled data distributions. RealMix demonstrates how SSL can be used in real world situations with limited access to both data and compute and guides further research in SSL with practical applicability in mind.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/14/2022

AuxMix: Semi-Supervised Learning with Unconstrained Unlabeled Data

Semi-supervised learning (SSL) has seen great strides when labeled data ...
research
08/08/2023

Enhancing Adversarial Robustness in Low-Label Regime via Adaptively Weighted Regularization and Knowledge Distillation

Adversarial robustness is a research area that has recently received a l...
research
06/14/2021

RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning

Semi-supervised learning (SSL) algorithms have had great success in rece...
research
11/01/2022

The Perils of Learning From Unlabeled Data: Backdoor Attacks on Semi-supervised Learning

Semi-supervised machine learning (SSL) is gaining popularity as it reduc...
research
02/11/2021

SelfHAR: Improving Human Activity Recognition through Self-training with Unlabeled Data

Machine learning and deep learning have shown great promise in mobile se...
research
07/16/2021

Semi-supervised Learning for Marked Temporal Point Processes

Temporal Point Processes (TPPs) are often used to represent the sequence...

Please sign up or login with your details

Forgot password? Click here to reset