Semi-Supervised Class Discovery

02/10/2020
by   Jeremy Nixon, et al.
0

One promising approach to dealing with datapoints that are outside of the initial training distribution (OOD) is to create new classes that capture similarities in the datapoints previously rejected as uncategorizable. Systems that generate labels can be deployed against an arbitrary amount of data, discovering classification schemes that through training create a higher quality representation of data. We introduce the Dataset Reconstruction Accuracy, a new and important measure of the effectiveness of a model's ability to create labels. We introduce benchmarks against this Dataset Reconstruction metric. We apply a new heuristic, class learnability, for deciding whether a class is worthy of addition to the training dataset. We show that our method applies to language through the CLINC Out-of-scope dataset. And we present a class discovery system that given only half of the classes at train time achieves 91% reconstruction accuracy on MNIST, 73% reconstruction accuracy on CIFAR-10 and 87% reconstruction accuracy on Fashion-MNIST, demonstrating the value of semi-supervised learning to automatically discovering classes.

READ FULL TEXT
research
01/24/2019

Semi-Unsupervised Learning with Deep Generative Models: Clustering and Classifying using Ultra-Sparse Labels

We introduce semi-unsupervised learning, an extreme case of semi-supervi...
research
02/06/2021

Open-World Semi-Supervised Learning

Supervised and semi-supervised learning methods have been traditionally ...
research
11/20/2017

Virtual Adversarial Ladder Networks For Semi-supervised Learning

Semi-supervised learning (SSL) partially circumvents the high cost of la...
research
08/17/2022

How does the degree of novelty impacts semi-supervised representation learning for novel class retrieval?

Supervised representation learning with deep networks tends to overfit t...
research
05/26/2022

Transfer and Share: Semi-Supervised Learning from Long-Tailed Data

Long-Tailed Semi-Supervised Learning (LTSSL) aims to learn from class-im...
research
09/30/2022

Semi-Supervised Single-View 3D Reconstruction via Prototype Shape Priors

The performance of existing single-view 3D reconstruction methods heavil...
research
06/19/2020

Semi-supervised time series classification method for quantum computing

In this paper we develop methods to solve two problems related to time s...

Please sign up or login with your details

Forgot password? Click here to reset