English

ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing

Computer Vision and Pattern Recognition 2022-08-01 v2

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.

Keywords

Cite

@article{arxiv.2202.11616,
  title  = {ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing},
  author = {Christoph Reinders and Frederik Schubert and Bodo Rosenhahn},
  journal= {arXiv preprint arXiv:2202.11616},
  year   = {2022}
}

Comments

Published at IJCAI-22

R2 v1 2026-06-24T09:51:30.197Z