Sarath Chandra Kothapalli

Add Semantic Attacks PyTorch

1

# Description Implementation of single semantic attacks on PyTorch image classifiers. The attacks are generated by perturbing hue, saturation, contrast, brightness, and rotation. Paper: https://openaccess.thecvf.com/content/CVPR2023/papers/Hsiung_Towards_Compositional_Adversarial_Robustness_Generalizing_Adversarial_Training_to_Composite_Semantic_CVPR_2023_paper.pdf Fixes #2126 ## Type of...

Implement semantic adversarial attacks

3

These are adversarial images that semantically represent the same object as the original images. For example, in [2] these are created by perturbing the following components of an image: *...

Deep-learning-based registration example

13

A simple example of deep-learning-based non-rigid image registration with the MNIST dataset, taking ideas from - [An Unsupervised Learning Model for Deformable Medical Image Registration](http://openaccess.thecvf.com/content_cvpr_2018/papers/Balakrishnan_An_Unsupervised_Learning_CVPR_2018_paper.pdf) - [Non-rigid image registration using...