# ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing

arXiv: https://arxiv.org/abs/2202.11616 · HTML: https://mlsanity.com/paper/2202.11616/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 54 references that are in the map.
- First posted on arXiv 23 Feb 2022.

## Builds on (most cited first, 27 of 27)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Big Transfer (BiT): General Visual Representation Learning](https://mlsanity.com/paper/1912.11370/) (2019)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [What is being transferred in transfer learning?](https://mlsanity.com/paper/2008.11687/) (2020)
- [TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation](https://mlsanity.com/paper/2103.10158/) (2021)
- [Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks](https://mlsanity.com/paper/1506.05751/) (2015)
- [Efficient Visual Pretraining with Contrastive Detection](https://mlsanity.com/paper/2103.10957/) (2021)
- [Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples](https://mlsanity.com/paper/2104.13963/) (2021)
- [Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks](https://mlsanity.com/paper/1910.01663/) (2019)
- [Do We Train on Test Data? Purging CIFAR of Near-Duplicates](https://mlsanity.com/paper/1902.00423/) (2019)
- [SuperMix: Supervising the Mixing Data Augmentation](https://mlsanity.com/paper/2003.05034/) (2020)
- [A Close Look at Deep Learning with Small Data](https://mlsanity.com/paper/2003.12843/) (2020)
- [On Aliased Resizing and Surprising Subtleties in GAN Evaluation](https://mlsanity.com/paper/2104.11222/) (2021)
- [Deep Learning on Small Datasets without Pre-Training using Cosine Loss](https://mlsanity.com/paper/1901.09054/) (2019)
- [Minimum-Distortion Embedding](https://mlsanity.com/paper/2103.02559/) (2021)
- [Small Data, Big Decisions: Model Selection in the Small-Data Regime](https://mlsanity.com/paper/2009.12583/) (2020)
- [TOAD-GAN: Coherent Style Level Generation from a Single Example](https://mlsanity.com/paper/2008.01531/) (2020)
- [Parametric Scattering Networks](https://mlsanity.com/paper/2107.09539/) (2021)
- [Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification](https://mlsanity.com/paper/2108.13122/) (2021)

## Built on by (most cited first, 4 of 4)

- [RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generation](https://mlsanity.com/paper/2411.13150/) (2024)
- [Take 5: Interpretable Image Classification with a Handful of Features](https://mlsanity.com/paper/2303.13166/) (2023)
- [Compensation Learning in Semantic Segmentation](https://mlsanity.com/paper/2304.13428/) (2023)
- [No Data Augmentation? Alternative Regularizations for Effective Training on Small Datasets](https://mlsanity.com/paper/2309.01694/) (2023)

## Abstract (arXiv)

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.