CURL: Co-trained Unsupervised Representation Learning for Image Classification

TL;DR

CURL introduces a semi-supervised image classification method that co-trains classifiers on different feature views, leveraging unsupervised learning to improve performance across various datasets and scenarios.

Contribution

The paper presents a novel co-training strategy combining multiple feature representations and unsupervised learning for semi-supervised image classification.

Findings

CURL outperforms existing supervised and semi-supervised methods.

Different feature fusion schemes enhance classification accuracy.

The approach is effective across multiple datasets and learning scenarios.

Abstract

In this paper we propose a strategy for semi-supervised image classification that leverages unsupervised representation learning and co-training. The strategy, that is called CURL from Co-trained Unsupervised Representation Learning, iteratively builds two classifiers on two different views of the data. The two views correspond to different representations learned from both labeled and unlabeled data and differ in the fusion scheme used to combine the image features. To assess the performance of our proposal, we conducted several experiments on widely used data sets for scene and object recognition. We considered three scenarios (inductive, transductive and self-taught learning) that differ in the strategy followed to exploit the unlabeled data. As image features we considered a combination of GIST, PHOG, and LBP as well as features extracted from a Convolutional Neural Network. Moreover, two embodiments of CURL are investigated: one using Ensemble Projection as unsupervised representation learning coupled with Logistic Regression, and one based on LapSVM. The results show that CURL clearly outperforms other supervised and semi-supervised learning methods in the state of the art.