Simon Korman
YOU?
Author Swipe
View article: Regularization for Unconditional Image Diffusion Models via Shifted Data Augmentation
Regularization for Unconditional Image Diffusion Models via Shifted Data Augmentation Open
Diffusion models are a powerful class of techniques in ML for generating realistic data, but they are highly prone to overfitting, especially with limited training data. While data augmentation such as image rotation can mitigate this issu…
View article: Unsupervised Representation Learning by Balanced Self Attention Matching
Unsupervised Representation Learning by Balanced Self Attention Matching Open
Many leading self-supervised methods for unsupervised representation learning, in particular those for embedding image features, are built on variants of the instance discrimination task, whose optimization is known to be prone to instabil…
View article: The Balanced-Pairwise-Affinities Feature Transform
The Balanced-Pairwise-Affinities Feature Transform Open
The Balanced-Pairwise-Affinities (BPA) feature transform is designed to upgrade the features of a set of input items to facilitate downstream matching or grouping related tasks. The transformed set encodes a rich representation of high ord…
View article: SeaThru-NeRF: Neural Radiance Fields in Scattering Media
SeaThru-NeRF: Neural Radiance Fields in Scattering Media Open
Research on neural radiance fields (NeRFs) for novel view generation is exploding with new models and extensions. However, a question that remains unanswered is what happens in underwater or foggy scenes where the medium strongly influence…
View article: Testing Connectedness of Images
Testing Connectedness of Images Open
We investigate algorithms for testing whether an image is connected. Given a proximity parameter ε ∈ (0,1) and query access to a black-and-white image represented by an n×n matrix of Boolean pixel values, a (1-sided error) connectedness te…
View article: NAN: Noise-Aware NeRFs for Burst-Denoising
NAN: Noise-Aware NeRFs for Burst-Denoising Open
Burst denoising is now more relevant than ever, as computational photography helps overcome sensitivity issues inherent in mobile phones and small cameras. A major challenge in burst-denoising is in coping with pixel misalignment, which wa…
View article: The Self-Optimal-Transport Feature Transform
The Self-Optimal-Transport Feature Transform Open
The Self-Optimal-Transport (SOT) feature transform is designed to upgrade the set of features of a data instance to facilitate downstream matching or grouping related tasks. The transformed set encodes a rich representation of high order r…
View article: Generative Adversarial Networks via a Composite Annealing of Noise and Diffusion
Generative Adversarial Networks via a Composite Annealing of Noise and Diffusion Open
Generative adversarial network (GAN) is a framework for generating fake data using a set of real examples. However, GAN is unstable in the training stage. In order to stabilize GANs, the noise injection has been used to enlarge the overlap…
View article: OATM: Occlusion Aware Template Matching by Consensus Set Maximization
OATM: Occlusion Aware Template Matching by Consensus Set Maximization Open
We present a novel approach to template matching that is efficient, can handle partial occlusions, and comes with provable performance guarantees. A key component of the method is a reduction that transforms the problem of searching a near…
View article: Latent RANSAC
Latent RANSAC Open
We present a method that can evaluate a RANSAC hypothesis in constant time, i.e. independent of the size of the data. A key observation here is that correct hypotheses are tightly clustered together in the latent parameter domain. In a man…
View article: Latent RANSAC
Latent RANSAC Open
We present a method that can evaluate a RANSAC hypothesis in constant time, i.e. independent of the size of the data. A key observation here is that correct hypotheses are tightly clustered together in the latent parameter domain. In a man…
View article: Deleting and Testing Forbidden Patterns in Multi-Dimensional Arrays
Deleting and Testing Forbidden Patterns in Multi-Dimensional Arrays Open
Analyzing multi-dimensional data is a fundamental problem in various areas of computer science. As the amount of data is often huge, it is desirable to obtain sublinear time algorithms to understand local properties of the data. We focus o…
View article: Testing Pattern-Freeness.
Testing Pattern-Freeness. Open
We consider the problem of testing pattern-freeness (PF): given a string $I$ and a fixed pattern $J$ of length $k$ over a finite alphabet $\Sigma$, decide whether $I$ is $J$-free (has no occurrence of $J$) or alternatively, one has to modi…
View article: Deleting and Testing Forbidden Patterns in Multi-Dimensional Arrays
Deleting and Testing Forbidden Patterns in Multi-Dimensional Arrays Open
Understanding the local behaviour of structured multi-dimensional data is a fundamental problem in various areas of computer science. As the amount of data is often huge, it is desirable to obtain sublinear time algorithms, and specificall…