Semi-supervised Learning with Contrastive Predicative Coding

05/25/2019
by   Jiaxing Wang, et al.
0

Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain. SSL algorithms based on deep neural networks have recently proven successful on standard benchmark tasks. However, many of them have thus far been either inflexible, inefficient or non-scalable. This paper explores recently developed contrastive predictive coding technique to improve discriminative power of deep learning models when a large portion of labels are absent. Two models, cpc-SSL and a class conditional variant (ccpc-SSL) are presented. They effectively exploit the unlabeled data by extracting shared information between different parts of the (high-dimensional) data. The proposed approaches are inductive, and scale well to very large datasets like ImageNet, making them good candidates in real-world large scale applications.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/24/2018

Realistic Evaluation of Deep Semi-Supervised Learning Algorithms

Semi-supervised learning (SSL) provides a powerful framework for leverag...
research
05/22/2019

Data-Efficient Image Recognition with Contrastive Predictive Coding

Large scale deep learning excels when labeled images are abundant, yet d...
research
09/09/2021

FedCon: A Contrastive Framework for Federated Semi-Supervised Learning

Federated Semi-Supervised Learning (FedSSL) has gained rising attention ...
research
06/05/2022

Semi-Supervised Learning for Mars Imagery Classification and Segmentation

With the progress of Mars exploration, numerous Mars image data are coll...
research
02/12/2022

Robust Deep Semi-Supervised Learning: A Brief Introduction

Semi-supervised learning (SSL) is the branch of machine learning that ai...
research
09/14/2017

Fast semi-supervised discriminant analysis for binary classification of large data-sets

High-dimensional data requires scalable algorithms. We propose and analy...
research
08/02/2023

Semi-supervised Cooperative Learning for Multiomics Data Fusion

Multiomics data fusion integrates diverse data modalities, ranging from ...

Please sign up or login with your details

Forgot password? Click here to reset