paper-with-me

홈 › Papers

Semi-supervised deep learning based on label propagation in a 2D embedded space

2020-08-02 · Barbara Caroline Benato, Jancarlo Ferreira Gomes, Alexandru Cristian Telea, Alexandre Xavier Falcão

While convolutional neural networks need large labeled sets for training images, expert human supervision of such datasets can be very laborious. Proposed solutions propagate labels from a small set of supervised images to a large set of unsupervised ones to obtain sufficient truly-and-artificially labeled samples to train a deep neural network model. Yet, such solutions need many supervised images for validation. We present a loop in which a deep neural network (VGG-16) is trained from a set with more correctly labeled samples along iterations, created by using t-SNE to project the features of its last max-pooling layer into a 2D embedded space in which labels are propagated using the Optimum-Path Forest semi-supervised classifier. As the labeled set improves along iterations, it improves the features of the neural network. We show that this can significantly improve classification results on test data (using only 1\% to 5\% of supervised samples) of three private challenging datasets and two public ones.

📄 PDF Abstract BibTeX arXiv:2008.00558

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Deep Clustering with Measure Propagation

2021-04-18 · Minhua Chen, Badrinath Jayakumar, Padmasundari Gopalakrishnan, Qiming Huang 외

Deep models have improved state-of-the-art for both supervised and unsupervised learning. For example, deep embedded clustering (DEC) has greatly improved the unsupervised clustering performance, by using stacked autoenc…

ClusteringDeep ClusteringRepresentation LearningShort Text Clustering+2

Linking data separation, visual separation, and classifier performance using pseudo-labeling by contrastive learning

2023-02-06 · Bárbara Caroline Benato, Alexandre Xavier Falcão, Alexandru-Cristian Telea

Lacking supervised data is an issue while training deep neural networks (DNNs), mainly when considering medical and biological data where supervision is expensive. Recently, Embedded Pseudo-Labeling (EPL) addressed this …

Contrastive Learning

Deep Transductive Semi-supervised Maximum Margin Clustering

2015-01-26 · Gang Chen

Semi-supervised clustering is an very important topic in machine learning and computer vision. The key challenge of this problem is how to learn a metric, such that the instances sharing the same label are more likely cl…

ClusteringTransductive Learning

Semi-supervised classification using a supervised autoencoder for biomedical applications

2022-08-22 · Cyprien Gille, Frederic Guyard, Michel Barlaud

In this paper we present a new approach to solve semi-supervised classification tasks for biomedical applications, involving a supervised autoencoder network. We create a network architecture that encodes labels into the…

General Classification

A multi-stage semi-supervised improved deep embedded clustering method for bearing fault diagnosis under the situation of insufficient labeled samples

2021-09-28 · Tongda Sun, Gang Yu

Although data-driven fault diagnosis methods have been widely applied, massive labeled data are required for model training. However, a difficulty of implementing this in real industries hinders the application of these …

ClusteringDeep ClusteringDiagnosticFault Diagnosis