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.
Stabilizes training of DNN for speech enhancement using PESQ scores.
This paper presents a novel CNN-based approach for synthesizing high-resolution LiDAR point cloud data. Our approach generates semantically and perceptually realistic results with guidance from specialized loss-functions. First, we utilize a modified per-point loss that addresses missing LiDAR point measurements. Secon…
New SSIM measure improves adversarial attacks' perceptual quality.
Perceptual Kalman filters maintain human-perceptual quality while processing data.
PeL separates sensory interface optimization from decision learning.
Paper proposes a method to protect DCNNs from adversarial attacks and poor quality images.
This paper uses diffusion models for lossy image compression, improving perceptual metrics and practicality.
Stochastic encoders outperform deterministic ones in 'perfect perceptual quality'.
In order to efficiently transmit and store speech signals, speech codecs create a minimally redundant representation of the input signal which is then decoded at the receiver with the best possible perceptual quality. In this work we demonstrate that a neural network architecture based on VQ-VAE with a WaveNet decoder …
Lossy compression algorithms are typically designed and analyzed through the lens of Shannon's rate-distortion theory, where the goal is to achieve the lowest possible distortion (e.g., low MSE or high SSIM) at any given bit rate. However, in recent years, it has become increasingly accepted that "low distortion" is no…
Traditionally, the vision community has devised algorithms to estimate the distance between an original image and images that have been subject to perturbations. Inspiration was usually taken from the human visual perceptual system and how the system processes different perturbations in order to replicate to what exten…
Paper introduces adversarial lossy compression for video artifacts reduction.
Paper presents a new video generation model using diffusion probabilistic methods.
We introduce autoregressive implicit quantile networks (AIQN), a fundamentally different approach to generative modeling than those commonly used, that implicitly captures the distribution using quantile regression. AIQN is able to achieve superior perceptual quality and improvements in evaluation metrics, without incu…
We propose a training method for deep neural network (DNN)-based source enhancement to increase objective sound quality assessment (OSQA) scores such as the perceptual evaluation of speech quality (PESQ). In many conventional studies, DNNs have been used as a mapping function to estimate time-frequency masks and traine…
A new loss function for VAEs improves image quality and efficiency.
New hierarchical VQ-VAE scheme improves image compression quality and features at low bitrates.
The ability to automatically estimate the quality and coverage of the samples produced by a generative model is a vital requirement for driving algorithm research. We present an evaluation metric that can separately and reliably measure both of these aspects in image generation tasks by forming explicit, non-parametric…
Quaternion Conformer GAN (QC-GAN) is a parameter-efficient speech enhancement framework that combines a Quaternion Conformer generator with MetricGAN-based training.
Improved image compression with diffusion models outperforming state-of-the-art methods.
Thanks to the growing availability of spoofing databases and rapid advances in using them, systems for detecting voice spoofing attacks are becoming more and more capable, and error rates close to zero are being reached for the ASVspoof2015 database. However, speech synthesis and voice conversion paradigms that are not…
Protein structure prediction has been a grand challenge problem in the structure biology over the last few decades. Protein quality assessment plays a very important role in protein structure prediction. In the paper, we propose a new protein quality assessment method which can predict both local and global quality of …
Deep neural networks (DNNs) have recently achieved state-of-the-art performance and provide significant progress in many machine learning tasks, such as image classification, speech processing, natural language processing, etc. However, recent studies have shown that DNNs are vulnerable to adversarial attacks. For inst…
Diffusion models optimize objectives similar to ELBO with Gaussian noise augmentation.
The paper assesses quality measures for machine learning models using cross-validation.
Automatically assesses the quality of online health articles.
Magnetic resonance (MR) imaging offers a wide variety of imaging techniques. A large amount of data is created per examination which needs to be checked for sufficient quality in order to derive a meaningful diagnosis. This is a manual process and therefore time- and cost-intensive. Any imaging artifacts originating fr…
PriorGrad improves speech synthesis models by using data-dependent adaptive priors.
Study improves data quality assessment for structural monitoring data.
Existing model-based reinforcement learning methods often study perception modeling and decision making separately. We introduce joint Perception and Control as Inference (PCI), a general framework to combine perception and control for partially observable environments through Bayesian inference. Based on the fact that…
Fastens diffusion model sampling by distillation.
In recent years there has been a growing interest in image generation through deep learning. While an important part of the evaluation of the generated images usually involves visual inspection, the inclusion of human perception as a factor in the training process is often overlooked. In this paper we propose an altern…
The Gestalt laws of perceptual organization, which describe how visual elements in an image are grouped and interpreted, have traditionally been thought of as innate despite their ecological validity. We use deep-learning methods to investigate whether natural scene statistics might be sufficient to derive the Gestalt …
A framework assesses the quality of crowdsourced weather data.
This paper explores using SSIM for better image generation in generative models.
Convolutional neural networks were recently employed to fully reconstruct fluid simulation data from a set of reduced parameters. However, since (de-)convolutions traditionally trained with supervised L1-loss functions do not discriminate between low and high frequencies in the data, the error is not minimized efficien…
This paper introduces a novel approach to in-painting where the identity of the object to remove or change is preserved and accounted for at inference time: Exemplar GANs (ExGANs). ExGANs are a type of conditional GAN that utilize exemplar information to produce high-quality, personalized in painting results. We propos…
Paper proposes a method to enhance low-quality retinal images using optimal transport.
A method merges two pretrained diffusion experts to improve image quality and likelihood.
Despite the breakthroughs in accuracy and speed of single image super-resolution using faster and deeper convolutional neural networks, one central problem remains largely unsolved: how do we recover the finer texture details when we super-resolve at large upscaling factors? The behavior of optimization-based super-res…
Paper proposes a method to make image model explanations robust to distortions.
Deep learning has brought an unprecedented progress in computer vision and significant advances have been made in predicting subjective properties inherent to visual data (e.g., memorability, aesthetic quality, evoked emotions, etc.). Recently, some research works have even proposed deep learning approaches to modify i…
Generative models assess quality on time-series data using ITS and FITD.
GAN normalizes CT scans for consistent radiomic feature values.
New method defends against unseen threat models using perceptual adversarial training.
PICLE uses probabilistic models to efficiently evaluate and compose modules for continual learning.
The paper introduces a method to assess machine translation quality with confidence intervals.
Framework for automatically assessing and correcting data quality issues without domain knowledge.