Iterative Self-Learning: Semi-Supervised Improvement to Dataset Volumes and Model Accuracy

2019-06-06 · Robert Dupre, Jiri Fajtl, Vasileios Argyriou, Paolo Remagnin

A novel semi-supervised learning technique is introduced based on a simple iterative learning cycle together with learned thresholding techniques and an ensemble decision support system. State-of-the-art model performance and increased training data volume are demonstrated, through the use of unlabelled data when training deeply learned classification models. Evaluation of the proposed approach is performed on commonly used datasets when evaluating semi-supervised learning techniques as well as a number of more challenging image classification datasets (CIFAR-100 and a 200 class subset of ImageNet).

📄 PDF Abstract BibTeX arXiv:1906.02823

Code (0)

등록된 구현이 없습니다.

Tasks

Classification General Classification image-classification Image ClassificationSelf-Learning

Debiased Self-Training for Semi-Supervised Learning

2022-02-15 · Baixu Chen, Junguang Jiang, Ximei Wang, Pengfei Wan 외

Deep neural networks achieve remarkable performances on a wide range of tasks with the aid of large-scale labeled datasets. Yet these datasets are time-consuming and labor-exhaustive to obtain on realistic tasks. To miti…

Object Recognition Scene Classification Semi-Supervised Image Classification Texture Classification

The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation

2021-03-31 · Eu Wern Teh, Terrance DeVries, Brendan Duke, Ruowei Jiang 외

We consider the task of semi-supervised semantic segmentation, where we aim to produce pixel-wise semantic object masks given only a small number of human-labeled training examples. We focus on iterative self-training me…

Semantic Segmentation Semi-Supervised Semantic Segmentation

A viable framework for semi-supervised learning on realistic dataset

2022-07-21 · Machine Learning 2022 7 · Hao Chang, Guochen Xie, Jun Yu, Qiang Ling 외

Semi-supervised Fine-Grained Recognition is a challenging task due to the difficulty of data imbalance, high inter-class similarity and domain mismatch. Recently, this field has witnessed giant leap and many methods have…

Iterative Graph Self-Distillation

2020-10-23 · HANLIN ZHANG, Shuai Lin, Weiyang Liu, Pan Zhou 외

Recently, there has been increasing interest in the challenge of how to discriminatively vectorize graphs. To address this, we propose a method called Iterative Graph Self-Distillation (IGSD) which learns graph-level rep…

Contrastive Learning Graph Learning Knowledge Distillation

Semi-supervised ASR by End-to-end Self-training

2020-01-24 · Yang Chen, Weiran Wang, Chao Wang

While deep learning based end-to-end automatic speech recognition (ASR) systems have greatly simplified modeling pipelines, they suffer from the data sparsity issue. In this work, we propose a self-training method with a…

Automatic Speech Recognition Automatic Speech Recognition (ASR)Data Augmentation Pseudo Label+2