CvS: Classification via Segmentation For Small Datasets

TL;DR

CvS is a novel classification approach for small datasets that leverages segmentation and label propagation to improve accuracy when data is limited.

Contribution

The paper introduces CvS, a cost-effective classification method that uses segmentation and label propagation to enhance performance on small datasets.

Findings

CvS outperforms previous methods on small datasets.

Segmentation-based labels improve classification accuracy.

Label propagation enables effective training with minimal manual annotations.

Abstract

Deep learning models have shown promising results in a wide range of computer vision applications across various domains. The success of deep learning methods relies heavily on the availability of a large amount of data. Deep neural networks are prone to overfitting when data is scarce. This problem becomes even more severe for neural network with classification head with access to only a few data points. However, acquiring large-scale datasets is very challenging, laborious, or even infeasible in some domains. Hence, developing classifiers that are able to perform well in small data regimes is crucial for applications with limited data. This paper presents CvS, a cost-effective classifier for small datasets that derives the classification labels from predicting the segmentation maps. We employ the label propagation method to achieve a fully segmented dataset with only a handful of manually segmented data. We evaluate the effectiveness of our framework on diverse problems showing that CvS is able to achieve much higher classification results compared to previous methods when given only a handful of examples.