mlsanityData to 14 Oct 2026

What augmentations are sensitive to hyper-parameters and why?

arXiv 2111.03861 ↗First posted 6 Nov 2021cs.CV cs.AI cs.LGcited by 0

Not on the map. Why?

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.

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

26 of 66 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  4. 2016Wide Residual Networkscited by 3,070
  5. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  6. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  7. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  8. 2018AutoAugment: Learning Augmentation Policies from Datacited by 730
  9. 2017Generative Adversarial Networks: An Overviewcited by 590
  10. 2018Albumentations: fast and flexible image augmentationscited by 560
  11. 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 370
  12. 2020On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practicecited by 182
14 more
  1. 2018Tunability: Importance of Hyperparameters of Machine Learning Algorithmscited by 99
  2. 2017Learning to Compose Domain-Specific Transformations for Data Augmentationcited by 91
  3. 2019What Can ResNet Learn Efficiently, Going Beyond Kernels?cited by 91
  4. 2017Smart Augmentation - Learning an Optimal Data Augmentation Strategycited by 54
  5. 2020KeepAugment: A Simple Information-Preserving Data Augmentation Approachcited by 52
  6. 2017A Bayesian Data Augmentation Approach for Learning Deep Modelscited by 50
  7. 2015Dreaming More Data: Class-dependent Distributions over Diffeomorphisms for Learned Data Augmentationcited by 24
  8. 2020Anomaly Detection based on Zero-Shot Outlier Synthesis and Hierarchical Feature Distillationcited by 18
  9. 2015Deep Image: Scaling up Image Recognitioncited by 16
  10. 2017Multi-label Class-imbalanced Action Recognition in Hockey Videos via 3D Convolutional Neural Networkscited by 12
  11. 2015Deep CNN Ensemble with Data Augmentation for Object Detectioncited by 10
  12. 2019SART - Similarity, Analogies, and Relatedness for Tatar Language: New Benchmark Datasets for Word Embeddings Evaluationcited by 5
  13. 2016A data augmentation methodology for training machine/deep learning gait recognition algorithmscited by 4
  14. 2017Seeking Optimum System Settings for Physical Activity Recognition on Smartwatchescited by 1

Built on by

Not cited yet.