# Optimal Layer Selection for Latent Data Augmentation

arXiv: https://arxiv.org/abs/2408.13426 · HTML: https://mlsanity.com/paper/2408.13426/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 26 references that are in the map.
- First posted on arXiv 24 Aug 2024.

## Builds on (most cited first, 23 of 23)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Efficient Neural Architecture Search via Parameter Sharing](https://mlsanity.com/paper/1802.03268/) (2018)
- [Progressive Neural Architecture Search](https://mlsanity.com/paper/1712.00559/) (2017)
- [Optimizing Millions of Hyperparameters by Implicit Differentiation](https://mlsanity.com/paper/1911.02590/) (2019)
- [DropBlock: A regularization method for convolutional networks](https://mlsanity.com/paper/1810.12890/) (2018)
- [Fast AutoAugment](https://mlsanity.com/paper/1905.00397/) (2019)
- [TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation](https://mlsanity.com/paper/2103.10158/) (2021)
- [Feature Space Augmentation for Long-Tailed Data](https://mlsanity.com/paper/2008.03673/) (2020)
- [Dataset Augmentation in Feature Space](https://mlsanity.com/paper/1702.05538/) (2017)
- [Shake-Shake regularization](https://mlsanity.com/paper/1705.07485/) (2017)
- [Scalable Gradient-Based Tuning of Continuous Regularization Hyperparameters](https://mlsanity.com/paper/1511.06727/) (2015)
- [ShakeDrop Regularization for Deep Residual Learning](https://mlsanity.com/paper/1802.02375/) (2018)
- [UniformAugment: A Search-free Probabilistic Data Augmentation Approach](https://mlsanity.com/paper/2003.14348/) (2020)
- [AutoDropout: Learning Dropout Patterns to Regularize Deep Networks](https://mlsanity.com/paper/2101.01761/) (2021)
- [OnlineAugment: Online Data Augmentation with Less Domain Knowledge](https://mlsanity.com/paper/2007.09271/) (2020)
- [Meta Approach to Data Augmentation Optimization](https://mlsanity.com/paper/2006.07965/) (2020)
- [When to Learn What: Model-Adaptive Data Augmentation Curriculum](https://mlsanity.com/paper/2309.04747/) (2023)
- [DP-Mix: Mixup-based Data Augmentation for Differentially Private Learning](https://mlsanity.com/paper/2311.01295/) (2023)
- [Self-paced Data Augmentation for Training Neural Networks](https://mlsanity.com/paper/2010.15434/) (2020)

## Abstract (arXiv)

While data augmentation (DA) is generally applied to input data, several studies have reported that applying DA to hidden layers in neural networks, i.e., feature augmentation, can improve performance. However, in previous studies, the layers to which DA is applied have not been carefully considered, often being applied randomly and uniformly or only to a specific layer, leaving room for arbitrariness. Thus, in this study, we investigated the trends of suitable layers for applying DA in various experimental configurations, e.g., training from scratch, transfer learning, various dataset settings, and different models. In addition, to adjust the suitable layers for DA automatically, we propose the adaptive layer selection (AdaLASE) method, which updates the ratio to perform DA for each layer based on the gradient descent method during training. The experimental results obtained on several image classification datasets indicate that the proposed AdaLASE method altered the ratio as expected and achieved high overall test accuracy.