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.
Improved TTS style transfer across disjoint datasets with adversarial cycle consistency.
Improved unsupervised word translation using adversarial autoencoder with cycle consistency and input reconstruction.
Novel unsupervised method for fast 3D image registration using cycle-consistent CNN.
New CycleGAN uses invertible generator for faster, less resource-intensive CT denoising.
End-to-end algorithm for W-2 distance using neural networks.
RCGAN improves anomaly detection by better recognizing anomalous samples.
CycleMorph improves image registration by preserving topology with cycle consistency.
This paper uses LLMs and cycle consistency for better machine translation evaluation.
New method uses cycle consistency to enforce invariance in latent space.
AlignFlow uses normalizing flows to model multiple domains efficiently.
Training a model to perform a task typically requires a large amount of data from the domains in which the task will be applied. However, it is often the case that data are abundant in some domains but scarce in others. Domain adaptation deals with the challenge of adapting a model trained from a data-rich source domai…
This work proposes a new method to match distributions across different spaces using cycle-consistent maps.
Mic2Mic reduces microphone variability for speech systems.
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…
New unsupervised image translation method detects changes without labeled data.
Improved neural network surrogates for ICF using manifold and cycle consistency.
New CNN method improves deconvolution microscopy without PSF measurement.
We propose a parallel-data-free voice-conversion (VC) method that can learn a mapping from source to target speech without relying on parallel data. The proposed method is general purpose, high quality, and parallel-data free and works without any extra data, modules, or alignment procedure. It also avoids over-smoothi…
Deep learning improves 3D microscopy resolution without matched target images.
The paper analyzes CycleGAN's error components for unpaired data generation.
Generative model creates meal images from ingredient descriptions.
A new method improves robustness in image translation by modeling uncertainty.
New method solves group synchronization with cycle-edge message passing.
In this work we study permutation synchronisation for the challenging case of partial permutations, which plays an important role for the problem of matching multiple objects (e.g. images or shapes). The term synchronisation refers to the property that the set of pairwise matchings is cycle-consistent, i.e. in the full…
Proposes a new method to improve target annotation in ATR.
Paper proposes a novel unsupervised feature learning approach for environmental sound classification.
Generating an image from its description is a challenging task worth solving because of its numerous practical applications ranging from image editing to virtual reality. All existing methods use one single caption to generate a plausible image. A single caption by itself, can be limited, and may not be able to capture…
Scalable algorithm for computing Wasserstein-2 barycenters without bias.
We formalize the problem of learning interdomain correspondences in the absence of paired data as Bayesian inference in a latent variable model (LVM), where one seeks the underlying hidden representations of entities from one domain as entities from the other domain. First, we introduce implicit latent variable models,…
Recent techniques built on Generative Adversarial Networks (GANs), such as Cycle-Consistent GANs, are able to learn mappings among different domains built from unpaired datasets, through min-max optimization games between generators and discriminators. However, it remains challenging to stabilize the training process a…
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…
Generative model simulates jet radiation patterns with high accuracy.
Novel method solves group synchronization with robust corruption tolerance.
Method maps imperfect simulations to observed stellar spectra using unsupervised domain adaptation.
Insufficient training data and severe class imbalance are often limiting factors when developing machine learning models for the classification of rare diseases. In this work, we address the problem of classifying bone lesions from X-ray images by increasing the small number of positive samples in the training set. We …
Adversarial fog tests autonomous navigation models.
Proposes DC3-GAN for diverse unsupervised conditional generation.
The matching of multiple objects (e.g. shapes or images) is a fundamental problem in vision and graphics. In order to robustly handle ambiguities, noise and repetitive patterns in challenging real-world settings, it is essential to take geometric consistency between points into account. Computationally, the multi-match…
The proposed model is aimed to reveal important patterns in the behavior of a simplified financial system. The patterns could be detected as regular cycles consisting of debt bubbles and crises. Financial cycles have a well defined structure and form periodic sequences along the axis of credit expansion while retaining…
In coronary CT angiography, a series of CT images are taken at different levels of radiation dose during the examination. Although this reduces the total radiation dose, the image quality during the low-dose phases is significantly degraded. To address this problem, here we propose a novel semi-supervised learning tech…
Unsupervised domain adaptation aiming to learn a specific task for one domain using another domain data has emerged to address the labeling issue in supervised learning, especially because it is difficult to obtain massive amounts of labeled data in practice. The existing methods have succeeded by reducing the differen…
We propose a learning-based filter that allows us to directly modify a synthetic speech waveform into a natural speech waveform. Speech-processing systems using a vocoder framework such as statistical parametric speech synthesis and voice conversion are convenient especially for a limited number of data because it is p…
Anomaly detection is a significant and hence well-studied problem. However, developing effective anomaly detection methods for complex and high-dimensional data remains a challenge. As Generative Adversarial Networks (GANs) are able to model the complex high-dimensional distributions of real-world data, they offer a pr…
Ideally, what confuses neural network should be confusing to humans. However, recent experiments have shown that small, imperceptible perturbations can change the network prediction. To address this gap in perception, we propose a novel approach for learning robust classifier. Our main idea is: adversarial examples for…
Robust image translation model for noisy labels.
Curriculum learning strategies improve GAN training speed and quality.
Unsupervised method removes satellite noise without paired data.
Masanao Aoki developed a new methodology for a basic problem of economics: deducing rigorously the macroeconomic dynamics as emerging from the interactions of many individual agents. This includes deduction of the fractal / intermittent fluctuations of macroeconomic quantities from the granularity of the mezo-economic …