A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
UNSB uses neural Schrödinger Bridge to solve unpaired image-to-image translation.
The paper tightens bounds for estimating Schrödinger potentials in unpaired data translation.
A new method for image translation without paired data.
New algorithm computes Schrödinger Bridge for unpaired data translation.
Synthetic image translation has significant potentials in autonomous transportation systems. That is due to the expense of data collection and annotation as well as the unmanageable diversity of real-words situations. The main issue with unpaired image-to-image translation is the ill-posed nature of the problem. In thi…
Recent GAN-based architectures have been able to deliver impressive performance on the general task of image-to-image translation. In particular, it was shown that a wide variety of image translation operators may be learned from two image sets, containing images from two different domains, without establishing an expl…
We tackle unsupervised anomaly detection (UAD), a problem of detecting data that significantly differ from normal data. UAD is typically solved by using density estimation. Recently, deep neural network (DNN)-based density estimators, such as Normalizing Flows, have been attracting attention. However, one of their draw…
FDBM models use fractional Brownian motion to model complex stochastic processes.
There has been remarkable recent work in unpaired image-to-image translation. However, they're restricted to translation on single pairs of distributions, with some exceptions. In this study, we extend one of these works to a scalable multidistribution translation mechanism. Our translation models not only converts fro…
A new method improves robustness in image translation by modeling uncertainty.
Federated CycleGAN enables privacy-preserving image translation without central data.
In the medical domain, the lack of large training data sets and benchmarks is often a limiting factor for training deep neural networks. In contrast to expensive manual labeling, computer simulations can generate large and fully labeled data sets with a minimum of manual effort. However, models that are trained on simu…
We present a framework for translating unlabeled images from one domain into analog images in another domain. We employ a progressively growing skip-connected encoder-generator structure and train it with a GAN loss for realistic output, a cycle consistency loss for maintaining same-domain translation identity, and a s…
Neural networks have proven their capabilities by outperforming many other approaches on regression or classification tasks on various kinds of data. Other astonishing results have been achieved using neural nets as data generators, especially in settings of generative adversarial networks (GANs). One special applicati…
OTRE uses OT to improve retinal images, outperforming existing methods.
This research shows how to learn shared representations from unpaired data.
Magnetic Resonance Imaging (MRI) of the brain can come in the form of different modalities such as T1-weighted and Fluid Attenuated Inversion Recovery (FLAIR) which has been used to investigate a wide range of neurological disorders. Current state-of-the-art models for brain tissue segmentation and disease classificati…
NOT learns optimal transport plans, kernel costs improve performance.
We propose a potential flow generator with optimal transport regularity, which can be easily integrated into a wide range of generative models including different versions of GANs and flow-based models. We show the correctness and robustness of the potential flow generator in several 2D problems, and illustrate t…
Paper investigates multimodal contrastive learning and incorporates unpaired data.
Domain Translation is the problem of finding a meaningful correspondence between two domains. Since in a majority of settings paired supervision is not available, much work focuses on Unsupervised Domain Translation (UDT) where data samples from each domain are unpaired. Following the seminal work of CycleGAN for UDT, …
Unpaired deep learning reconstructs MRI images from accelerated data.
The paper analyzes CycleGAN's error components for unpaired data generation.
Text-based analysis methods allow to reveal privacy relevant author attributes such as gender, age and identify of the text's author. Such methods can compromise the privacy of an anonymous author even when the author tries to remove privacy sensitive content. In this paper, we propose an automatic method, called Adver…
Unpaired multi-domain causal representation learning is possible with sufficient conditions.
LSDM uses unpaired data to match latent space distributions for generative modeling.
Proposes a new method to improve target annotation in ATR.
Although voice conversion (VC) algorithms have achieved remarkable success along with the development of machine learning, superior performance is still difficult to achieve when using nonparallel data. In this paper, we propose using a cycle-consistent adversarial network (CycleGAN) for nonparallel data-based VC train…
In this paper, we describe the "implicit autoencoder" (IAE), a generative autoencoder in which both the generative path and the recognition path are parametrized by implicit distributions. We use two generative adversarial networks to define the reconstruction and the regularization cost functions of the implicit autoe…
Study on estimating causal effects with limited data and multiple environments.
This paper tackles unpaired data in multi-view learning, proposing a new framework and models.
Model learns association between text and speech without paired data.
The paper proves probabilistic alignment between unseen modalities using contrastive learning.
Pseudo healthy synthesis, i.e. the creation of a subject-specific `healthy' image from a pathological one, could be helpful in tasks such as anomaly detection, understanding changes induced by pathology and disease or even as data augmentation. We treat this task as a factor decomposition problem: we aim to separate wh…
Unpaired image-to-image translation has attracted significant interest due to the invention of CycleGAN, a method which utilizes a combination of adversarial and cycle consistency losses to avoid the need for paired data. It is known that the CycleGAN problem might admit multiple solutions, and our goal in this paper i…
Paper presents a method to align unpaired samples across different modalities.
New method identifies shared components from unpaired multimodal mixtures.
Paper proposes a method to enhance low-quality retinal images using optimal transport.
We present KERMIT, a simple insertion-based approach to generative modeling for sequences and sequence pairs. KERMIT models the joint distribution and its decompositions (i.e., marginals and conditionals) using a single neural network and, unlike much prior work, does not rely on a prespecified factorization of the dat…
The paper proposes a method to estimate joint probability from unpaired data using entropic transport kernels.
Increasingly many real world tasks involve data in multiple modalities or views. This has motivated the development of many effective algorithms for learning a common latent space to relate multiple domains. However, most existing cross-view learning algorithms assume access to paired data for training. Their applicabi…
MFM improves generative model interpolations by learning approximate geodesics on data manifolds.
LightSBB-M improves generative diffusion modeling with lower 2-Wasserstein distances.
Selfie and cartoon are two popular artistic forms that are widely presented in our daily life. Despite the great progress in image translation/stylization, few techniques focus specifically on selfie cartoonization, since cartoon images usually contain artistic abstraction (e.g., large smoothing areas) and exaggeration…
Spatial studies of transcriptome provide biologists with gene expression maps of heterogeneous and complex tissues. However, most experimental protocols for spatial transcriptomics suffer from the need to select beforehand a small fraction of genes to be quantified over the entire transcriptome. Standard single-cell RN…
A new framework for generative modeling using value-driven transport.
DPOT uses deep learning to compute optimal transport efficiently.
A new method combines energy-based models and entropy-regularized optimal transport.