Open AccessPosted Content
Pseudo-Representation Labeling Semi-Supervised Learning.
Song-Bo Yang,Tian-Li Yu +1 more
Reads0
Chats0
TLDR
The pseudo-representation labeling is a simple and flexible framework that utilizes pseudo-labeling techniques to iteratively label a small amount of unlabeled data and use them as training data and outperforms the current state-of-the-art semi-supervised learning methods in industrial types of classification problems such as the WM-811K wafer map and the MIT-BIH Arrhythmia dataset.Abstract:
In recent years, semi-supervised learning (SSL) has shown tremendous success in leveraging unlabeled data to improve the performance of deep learning models, which significantly reduces the demand for large amounts of labeled data. Many SSL techniques have been proposed and have shown promising performance on famous datasets such as ImageNet and CIFAR-10. However, some exiting techniques (especially data augmentation based) are not suitable for industrial applications empirically. Therefore, this work proposes the pseudo-representation labeling, a simple and flexible framework that utilizes pseudo-labeling techniques to iteratively label a small amount of unlabeled data and use them as training data. In addition, our framework is integrated with self-supervised representation learning such that the classifier gains benefits from representation learning of both labeled and unlabeled data. This framework can be implemented without being limited at the specific model structure, but a general technique to improve the existing model. Compared with the existing approaches, the pseudo-representation labeling is more intuitive and can effectively solve practical problems in the real world. Empirically, it outperforms the current state-of-the-art semi-supervised learning methods in industrial types of classification problems such as the WM-811K wafer map and the MIT-BIH Arrhythmia dataset.read more
Citations
More filters
Proceedings ArticleDOI
Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation
TL;DR: Xia et al. as discussed by the authors proposed a cross-domain adaptive clustering loss to group features of unlabeled target data into clusters and perform cluster-wise feature alignment across the source and target domains.
References
More filters
Posted Content
Colorful Image Colorization
TL;DR: In this article, the problem of hallucinating a plausible color version of the photograph is addressed by posing it as a classification task and using class-balancing at training time to increase the diversity of colors in the result.
Journal ArticleDOI
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
TL;DR: Virtual adversarial training (VAT) as discussed by the authors is a regularization method based on virtual adversarial loss, which is a measure of local smoothness of the conditional label distribution given input.
Proceedings Article
RandAugment: Practical Automated Data Augmentation with a Reduced Search Space
TL;DR: This work proposes a simplified search space that vastly reduces the computational expense of automated augmentation, and permits the removal of a separate proxy task.
Proceedings Article
A Simple Weight Decay Can Improve Generalization
Anders Krogh,John Hertz +1 more
TL;DR: It is proven that a weight decay has two effects in a linear network, and it is shown how to extend these results to networks with hidden layers and non-linear units.
Posted Content
mixup: Beyond Empirical Risk Minimization
TL;DR: Mixup as discussed by the authors trains a neural network on convex combinations of pairs of examples and their labels, and regularizes the neural network to favor simple linear behavior in between training examples, which improves the generalization of state-of-the-art neural network architectures.
Related Papers (5)
A robust semi-supervised learning approach via mixture of label information
Yun Yang,Xingchen Liu +1 more