# Extreme Image Transformations Facilitate Robust Latent Object Representations

arXiv: https://arxiv.org/abs/2310.07725 · HTML: https://mlsanity.com/paper/2310.07725/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 77 references that are in the map.
- First posted on arXiv 19 Sep 2023.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [Countering Adversarial Images using Input Transformations](https://mlsanity.com/paper/1711.00117/) (2017)
- [Feature Denoising for Improving Adversarial Robustness](https://mlsanity.com/paper/1812.03411/) (2018)
- [Adversarial Examples Improve Image Recognition](https://mlsanity.com/paper/1911.09665/) (2019)
- [Generalisation in humans and deep neural networks](https://mlsanity.com/paper/1808.08750/) (2018)
- [Bag of Tricks for Adversarial Training](https://mlsanity.com/paper/2010.00467/) (2020)
- [Adversarial Training and Robustness for Multiple Perturbations](https://mlsanity.com/paper/1904.13000/) (2019)
- [Are Labels Required for Improving Adversarial Robustness?](https://mlsanity.com/paper/1905.13725/) (2019)
- [Generative Adversarial Perturbations](https://mlsanity.com/paper/1712.02328/) (2017)
- [Learning to See by Looking at Noise](https://mlsanity.com/paper/2106.05963/) (2021)
- [RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real](https://mlsanity.com/paper/2006.09001/) (2020)
- [Improving Adversarial Robustness of Ensembles with Diversity Training](https://mlsanity.com/paper/1901.09981/) (2019)
- [Rectifying the Shortcut Learning of Background for Few-Shot Learning](https://mlsanity.com/paper/2107.07746/) (2021)
- [Robust and Accurate Object Detection via Adversarial Learning](https://mlsanity.com/paper/2103.13886/) (2021)
- [Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks](https://mlsanity.com/paper/2006.07123/) (2020)
- [Encoding Robustness to Image Style via Adversarial Feature Perturbations](https://mlsanity.com/paper/2009.08965/) (2020)
- [Tracking Without Re-recognition in Humans and Machines](https://mlsanity.com/paper/2105.13351/) (2021)
- [Real2Sim or Sim2Real: Robotics Visual Insertion using Deep Reinforcement Learning and Real2Sim Policy Adaptation](https://mlsanity.com/paper/2206.02679/) (2022)
- [Extreme Image Transformations Affect Humans and Machines Differently](https://mlsanity.com/paper/2212.13967/) (2022)
- [The constitution of visual perceptual units in the functional architecture of V1](https://mlsanity.com/paper/1406.0289/) (2014)
- [The Challenge of Appearance-Free Object Tracking with Feedforward Neural Networks](https://mlsanity.com/paper/2110.02772/) (2021)

## Abstract (arXiv)

Adversarial attacks can affect the object recognition capabilities of machines in wild. These can often result from spurious correlations between input and class labels, and are prone to memorization in large networks. While networks are expected to do automated feature selection, it is not effective at the scale of the object. Humans, however, are able to select the minimum set of features required to form a robust representation of an object. In this work, we show that finetuning any pretrained off-the-shelf network with Extreme Image Transformations (EIT) not only helps in learning a robust latent representation, it also improves the performance of these networks against common adversarial attacks of various intensities. Our EIT trained networks show strong activations in the object regions even when tested with more intense noise, showing promising generalizations across different kinds of adversarial attacks.