ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing

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. Code is available at https://github.com/creinders/ChimeraMix.

Cite

Text

Reinders et al. "ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing." International Joint Conference on Artificial Intelligence, 2022. doi:10.24963/IJCAI.2022/181

Markdown

[Reinders et al. "ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing." International Joint Conference on Artificial Intelligence, 2022.](https://mlanthology.org/ijcai/2022/reinders2022ijcai-chimeramix/) doi:10.24963/IJCAI.2022/181

BibTeX

@inproceedings{reinders2022ijcai-chimeramix,
  title     = {{ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing}},
  author    = {Reinders, Christoph and Schubert, Frederik and Rosenhahn, Bodo},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2022},
  pages     = {1298-1305},
  doi       = {10.24963/IJCAI.2022/181},
  url       = {https://mlanthology.org/ijcai/2022/reinders2022ijcai-chimeramix/}
}