# Data Augmentation with Manifold Exploring Geometric Transformations for Increased Performance and Robustness

arXiv: https://arxiv.org/abs/1901.04420 · HTML: https://mlsanity.com/paper/1901.04420/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jan 2019.

## Built on by (most cited first, 7 of 7)

- [A Survey of Data Augmentation Approaches for NLP](https://mlsanity.com/paper/2105.03075/) (2021)
- [A Survey of Automated Data Augmentation Algorithms for Deep Learning-based Image Classification Tasks](https://mlsanity.com/paper/2206.06544/) (2022)
- [Hybrid Deep Learning Model using SPCAGAN Augmentation for Insider Threat Analysis](https://mlsanity.com/paper/2203.02855/) (2022)
- [The Causal Structure of Domain Invariant Supervised Representation Learning](https://mlsanity.com/paper/2208.06987/) (2022)
- [Joint Optimization of Class-Specific Training- and Test-Time Data Augmentation in Segmentation](https://mlsanity.com/paper/2305.19084/) (2023)
- [Mitigating Data Scarcity for Large Language Models](https://mlsanity.com/paper/2302.01806/) (2023)
- [Controlled Paraphrase Geometry in Sentence Embedding Space: Local Manifold Modeling and Latent Probing](https://mlsanity.com/paper/2605.01073/) (2026)

## Abstract (arXiv)

In this paper we propose a novel augmentation technique that improves not only the performance of deep neural networks on clean test data, but also significantly increases their robustness to random transformations, both affine and projective. Inspired by ManiFool, the augmentation is performed by a line-search manifold-exploration method that learns affine geometric transformations that lead to the misclassification on an image, while ensuring that it remains on the same manifold as the training data. This augmentation method populates any training dataset with images that lie on the border of the manifolds between two-classes and maximizes the variance the network is exposed to during training. Our method was thoroughly evaluated on the challenging tasks of fine-grained skin lesion classification from limited data, and breast tumor classification of mammograms. Compared with traditional augmentation methods, and with images synthesized by Generative Adversarial Networks our method not only achieves state-of-the-art performance but also significantly improves the network's robustness.