23 datasets found

The dataset used in the paper is a graph-based active learning problem, where the goal is to achieve a low error rate while querying as few nodes as possible.

Self-training is an important technique for solving semi-supervised learning problems. It leverages unlabeled data by generating pseudo-labels and combining them with a limited...

The shootout dataset is a regression dataset containing information about the reflectance spectra of pharmaceutical tablets.

The dataset is a spam classification dataset containing 4,600 emails labeled as spam or not.

The auto-mpg dataset is a regression dataset containing information about the fuel efficiency of various car models.

Semi-supervised learning (SSL) has been a fundamental challenge in machine learning for decades. The primary family of SSL algorithms, known as pseudo-labeling, involves...

Sequential sensor data is generated in a wide variety of practical applications. A fundamental challenge involves learning effective classifiers for such sequential data. While...

A dataset for semi-supervised learning of echocardiogram views

A dataset for semi-supervised learning of echocardiogram views

A dataset for semi-supervised learning of echocardiogram views

A new semi-supervised learning benchmark for classifying view and diagnosing aortic stenosis from the 6th Ma-

Semi-supervised learning from uncurated unlabelled data

Self-supervised and semi-supervised learning for GANs

Semi-supervised conditional GANs

QS-TTS is a semi-supervised TTS framework based on VQ-S3RL to effectively utilize more unlabeled speech audio to improve TTS quality while reducing its requirements for...

The proposed end-to-end pseudo-label based semi-supervised object detection framework, which simultaneously performs pseudo-labeling for unlabelled images and trains a detector...

EEG-based emotion recognition often requires sufficient labeled training samples to build an effective computational model. Labeling EEG data, on the other hand, is often...

Open-Set Semi-Supervised Object Detection aims to leverage the unconstrained unlabeled images to improve an object detector trained with the available labeled data.

Federated Noisy Student Training for Automatic Speech Recognition

GraphXCOVID: Explainable Deep Graph Diffusion Pseudo-Labelling for Identifying COVID-19 on Chest X-rays