Skip to search formSkip to main contentSkip to account menu

Explainability Methods for Graph Convolutional Neural Networks

This paper develops the graph analogues of three prominent explainability methods for convolutional neural networks: contrastive gradient-based (CG) saliency maps, Class Activation Mapping (CAM), and Excitation Back-Propagation (EB) and their variants, gradient-weighted CAM (Grad-CAM) and contrastive EB (c-EB).
View on IEEE (opens in a new tab)

Generalized Sliced Wasserstein Distances

The generalized Radon transform is utilized to define a new family of distances for probability measures, which are called generalized sliced-Wasserstein (GSW) distances, and it is shown that, similar to the SW distance, the GSW distance can be extended to a maximum GSW (max- GSW) distance.
View PDF on arXiv (opens in a new tab)

Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs

The concept of Universal Litmus Patterns (ULPs) is introduced, which enable one to reveal backdoor attacks by feeding these universal patterns to the network and analyzing the output (i.e., classifying the network as `clean' or `corrupted').
View on IEEE (opens in a new tab)

Image to Image Translation for Domain Adaptation

This work proposes the novel use of the recently proposed unpaired image-to-image translation framework to constrain the features extracted by the backbone encoder network, and applies it to domain adaptation between MNIST, USPS, and SVHN datasets, and Amazon, Webcam and DSLR Office datasets in classification tasks, and also between GTA5 and Cityscapes datasets for a segmentation task.
View on IEEE (opens in a new tab)

Sliced Wasserstein Auto-Encoders

View Paper (opens in a new tab)

Sliced-Wasserstein Autoencoder: An Embarrassingly Simple Generative Model

Sliced-Wasserstein Autoencoders (SWAE) are introduced, which are generative models that enable one to shape the distribution of the latent space into any samplable probability distribution without the need for training an adversarial network or defining a closed-form for the distribution.
View PDF on arXiv (opens in a new tab)

Optimal Mass Transport: Signal processing and machine-learning applications

A practical overview of the mathematical underpinnings of mass transport-related methods, including numerical implementation, are provided as well as a review, with demonstrations, of several applications.
View on IEEE (opens in a new tab)

Sliced Wasserstein Kernels for Probability Distributions

This work provides a new perspective on the application of optimal transport flavored distances through kernel methods in machine learning tasks and provides a family of provably positive definite kernels based on the Sliced Wasserstein distance.
View on IEEE (opens in a new tab)

Sliced Wasserstein Distance for Learning Gaussian Mixture Models

This work proposes an alternative formulation for estimating the GMM parameters using the sliced Wasserstein distance, which gives rise to a new algorithm that can estimate high-dimensional data distributions more faithfully than the EM algorithm.
View on IEEE (opens in a new tab)

The Radon Cumulative Distribution Transform and Its Application to Image Classification

This work describes a nonlinear, invertible, low-level image processing transform based on combining the well-known Radon transform for image data, and the 1D cumulative distribution transform proposed earlier and shows that it can often render certain problems linearly separable in a transform space.
View on IEEE (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)