Ensemble Learning with Sparse Hypercolumns

TL;DR

This paper explores the use of sparse hypercolumns and ensemble learning for image segmentation, demonstrating improved performance in low-shot scenarios and addressing computational challenges through stratified subsampling.

Contribution

It introduces a method combining stratified subsampling with ensemble learning on sparse hypercolumns for efficient and effective image segmentation, especially in low-data regimes.

Findings

Sparse hypercolumns with stratified subsampling improve segmentation accuracy.

Ensemble methods outperform baseline models in low-shot settings.

Logistic Regression is most effective with very limited data.

Abstract

Directly inspired by findings in biological vision, high-dimensional hypercolumns are feature vectors built by concatenating multi-scale activations of convolutional neural networks for a single image pixel location. Together with powerful classifiers, they can be used for image segmentation i.e. pixel classification. However, in practice, there are only very few works dedicated to the use of hypercolumns. One reason is the computational complexity of processing concatenated dense hypercolumns that grows linearly with the size $N$ of the training set. In this work, we address this challenge by applying stratified subsampling to the VGG16 based hypercolumns. Furthermore, we investigate the performance of ensemble learning on sparse hypercolumns. Our experiments on a brain tumor dataset show that stacking and voting ensembles deliver competitive performance, but in the extreme low-shot case of $N \leq 20$, a simple Logistic Regression classifier is the most effective method. For 10% stratified subsampling rate, our best average Dice score is 0.66 for $N=20$. This is a statistically significant improvement of 24.53% over the standard multi-scale UNet baseline ($p$-value = $[3.07e-11]$, Wilcoxon signed-rank test), which is less effective due to overfitting.