Deep Nearest Class Mean Model for Incremental Odor Classification

TL;DR

This paper introduces a Deep Nearest Class Mean (DNCM) model that effectively handles incremental odor classification by dynamically integrating new classes over time using deep learning and nearest class mean methods.

Contribution

The paper presents a novel DNCM model that combines deep neural networks with incremental learning capabilities for odor classification tasks.

Findings

Efficiently integrates new odor classes with few training samples.

Outperforms traditional static models in incremental scenarios.

Demonstrates robustness with limited data for new classes.

Abstract

In recent years, more machine learning algorithms have been applied to odor classification. These odor classification algorithms usually assume that the training datasets are static. However, for some odor recognition tasks, new odor classes continually emerge. That is, the odor datasets are dynamically growing while both training samples and number of classes are increasing over time. Motivated by this concern, this paper proposes a Deep Nearest Class Mean (DNCM) model based on the deep learning framework and nearest class mean method. The proposed model not only leverages deep neural network to extract deep features, but is also able to dynamically integrate new classes over time. In our experiments, the DNCM model was initially trained with 10 classes, then 25 new classes are integrated. Experiment results demonstrate that the proposed model is very efficient for incremental odor classification, especially for new classes with only a small number of training examples.