Two Cycle Learning: Clustering Based Regularisation for Deep Semi-Supervised Classification

01/15/2020
by   Philip Sellars, et al.
0

This works addresses the challenge of classification with minimal annotations. Obtaining annotated data is time consuming, expensive and can require expert knowledge. As a result, there is an acceleration towards semi-supervised learning (SSL) approaches which utilise large amounts of unlabelled data to improve classification performance. The vast majority of SSL approaches have focused on implementing the low-density separation assumption, in which the idea is that decision boundaries should lie in low density regions. However, they have implemented this assumption by treating the dataset as a set of individual attributes rather than as a global structure, which limits the overall performance of the classifier. Therefore, in this work, we go beyond this implementation and propose a novel SSL framework called two-cycle learning. For the first cycle, we use clustering based regularisation that allows for improved decision boundaries as well as features that generalises well. The second cycle is set as a graph based SSL that take advantages of the richer discriminative features of the first cycle to significantly boost the accuracy of generated pseudo-labels. We evaluate our two-cycle learning method extensively across multiple datasets, outperforming current approaches.

READ FULL TEXT
research
03/13/2020

The GraphNet Zoo: A Plug-and-Play Framework for Deep Semi-Supervised Classification

We consider the problem of classifying a medical image dataset when we h...
research
06/08/2021

LaplaceNet: A Hybrid Energy-Neural Model for Deep Semi-Supervised Classification

Semi-supervised learning has received a lot of recent attention as it al...
research
10/16/2021

Pseudo-label refinement using superpixels for semi-supervised brain tumour segmentation

Training neural networks using limited annotations is an important probl...
research
06/07/2020

Optimally Combining Classifiers for Semi-Supervised Learning

This paper considers semi-supervised learning for tabular data. It is wi...
research
03/25/2022

Noisy Boundaries: Lemon or Lemonade for Semi-supervised Instance Segmentation?

Current instance segmentation methods rely heavily on pixel-level annota...
research
05/22/2022

Deep Low-Density Separation for Semi-Supervised Classification

Given a small set of labeled data and a large set of unlabeled data, sem...
research
05/04/2022

Semi-Supervised Cascaded Clustering for Classification of Noisy Label Data

The performance of supervised classification techniques often deteriorat...

Please sign up or login with your details

Forgot password? Click here to reset