Comment on "Ensemble Projection for Semi-supervised Image Classification"

TL;DR

This paper critiques the Ensemble Projections method for semi-supervised image classification, arguing that its reported results are not reliable and that the method performs poorly in practice.

Contribution

It provides a critical analysis of Ensemble Projections, highlighting methodological issues and demonstrating its limited effectiveness for semi-supervised learning.

Findings

Reported results were not well conducted

Ensemble Projections performs poorly in semi-supervised learning

The critique questions the validity of previous claims

Abstract

In a series of papers by Dai and colleagues [1,2], a feature map (or kernel) was introduced for semi- and unsupervised learning. This feature map is build from the output of an ensemble of classifiers trained without using the ground-truth class labels. In this critique, we analyze the latest version of this series of papers, which is called Ensemble Projections [2]. We show that the results reported in [2] were not well conducted, and that Ensemble Projections performs poorly for semi-supervised learning.