.png){kind=icon}
Return
Naive semi-supervised deep learning using pseudo-label
.png){kind=icon}
PRE
AI
DOI：10.1007/s12083-018-0702-9.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
To facilitate the utilization of large-scale unlabeled data, we propose a simple and effective method for semi-supervised deep learning that improves upon the performance of the deep learning model. First, we train a classifier and use its outputs on unlabeled data as pseudo-labels. Then, we pre-train the deep learning model with the pseudo-labeled data and fine-tune it with the labeled data. The repetition of pseudo-labeling, pre-training, and fine-tuning is called naive semi-supervised deep learning. We apply this method to the MNIST, CIFAR-10, and IMDB data sets, which are each divided into a small labeled data set and a large unlabeled data set by us. Our method achieves significant performance improvements compared to the deep learning model without pre-training. We further analyze the factors that affect our method to provide a better understanding of how to utilize naive semi-supervised deep learning in practical application.
Keywords:
Deep learning
Semi-supervised learning
Pseudo-label
Pre-training
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
2.6
Papers:
2.2K
Citations:
2.9K
Organization
No organization information available
Cited Papers
.png){kind=icon}
ShareSaveTORTICOLLIS SPASTICA: SUGGESTED ETIOLOGIC RELATION TO THE VESTIBULAR APPARATUS; REPORT OF A CASE
PREAI
ShareSaveShareSaveShareSaveShareSaveShareSave
ShareSave
View more