ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing

TL;DR

ChimeraMix is a novel data augmentation method that generates new training samples by combining image features guided by masks, significantly improving classification accuracy on small datasets without extra data.

Contribution

The paper introduces ChimeraMix, a new architecture for data augmentation that composes images by mixing features guided by masks, enhancing small dataset learning.

Findings

ChimeraMix outperforms state-of-the-art methods on benchmark datasets.

It improves classification accuracy on small datasets without additional data.

The method is effective across multiple datasets like ciFAIR-10, STL-10, and ciFAIR-100.

Abstract

Deep convolutional neural networks require large amounts of labeled data samples. For many real-world applications, this is a major limitation which is commonly treated by augmentation methods. In this work, we address the problem of learning deep neural networks on small datasets. Our proposed architecture called ChimeraMix learns a data augmentation by generating compositions of instances. The generative model encodes images in pairs, combines the features guided by a mask, and creates new samples. For evaluation, all methods are trained from scratch without any additional data. Several experiments on benchmark datasets, e.g. ciFAIR-10, STL-10, and ciFAIR-100, demonstrate the superior performance of ChimeraMix compared to current state-of-the-art methods for classification on small datasets.