# What augmentations are sensitive to hyper-parameters and why?

arXiv: https://arxiv.org/abs/2111.03861 · HTML: https://mlsanity.com/paper/2111.03861/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 66 references that are in the map.
- First posted on arXiv 6 Nov 2021.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [Generative Adversarial Networks: An Overview](https://mlsanity.com/paper/1710.07035/) (2017)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [The Effectiveness of Data Augmentation in Image Classification using Deep Learning](https://mlsanity.com/paper/1712.04621/) (2017)
- [On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice](https://mlsanity.com/paper/2007.15745/) (2020)
- [Tunability: Importance of Hyperparameters of Machine Learning Algorithms](https://mlsanity.com/paper/1802.09596/) (2018)
- [Learning to Compose Domain-Specific Transformations for Data Augmentation](https://mlsanity.com/paper/1709.01643/) (2017)
- [What Can ResNet Learn Efficiently, Going Beyond Kernels?](https://mlsanity.com/paper/1905.10337/) (2019)
- [Smart Augmentation - Learning an Optimal Data Augmentation Strategy](https://mlsanity.com/paper/1703.08383/) (2017)
- [KeepAugment: A Simple Information-Preserving Data Augmentation Approach](https://mlsanity.com/paper/2011.11778/) (2020)
- [A Bayesian Data Augmentation Approach for Learning Deep Models](https://mlsanity.com/paper/1710.10564/) (2017)
- [Dreaming More Data: Class-dependent Distributions over Diffeomorphisms for Learned Data Augmentation](https://mlsanity.com/paper/1510.02795/) (2015)
- [Anomaly Detection based on Zero-Shot Outlier Synthesis and Hierarchical Feature Distillation](https://mlsanity.com/paper/2010.05119/) (2020)
- [Deep Image: Scaling up Image Recognition](https://mlsanity.com/paper/1501.02876/) (2015)
- [Multi-label Class-imbalanced Action Recognition in Hockey Videos via 3D Convolutional Neural Networks](https://mlsanity.com/paper/1709.01421/) (2017)
- [Deep CNN Ensemble with Data Augmentation for Object Detection](https://mlsanity.com/paper/1506.07224/) (2015)
- [SART - Similarity, Analogies, and Relatedness for Tatar Language: New Benchmark Datasets for Word Embeddings Evaluation](https://mlsanity.com/paper/1904.00365/) (2019)
- [A data augmentation methodology for training machine/deep learning gait recognition algorithms](https://mlsanity.com/paper/1610.07570/) (2016)
- [Seeking Optimum System Settings for Physical Activity Recognition on Smartwatches](https://mlsanity.com/paper/1706.01720/) (2017)

## Abstract (arXiv)

We apply augmentations to our dataset to enhance the quality of our predictions and make our final models more resilient to noisy data and domain drifts. Yet the question remains, how are these augmentations going to perform with different hyper-parameters? In this study we evaluate the sensitivity of augmentations with regards to the model's hyper parameters along with their consistency and influence by performing a Local Surrogate (LIME) interpretation on the impact of hyper-parameters when different augmentations are applied to a machine learning model. We have utilized Linear regression coefficients for weighing each augmentation. Our research has proved that there are some augmentations which are highly sensitive to hyper-parameters and others which are more resilient and reliable.