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 self-supervised denoising for Poisson-Gaussian noise.
Paper analyzes self-supervised image denoising with denatured data.
Self-supervised method predicts clean signal and noise distribution from noisy images.
DiffDenoise preserves fine structures in medical images using conditional diffusion models.
A method for collecting human supervision that combines rules and instance labels.
New method denoises images without clean reference using Tweedie distributions.
New method improves image denoising with fewer parameters and less data.
UDVD uses deep learning to denoise videos without supervision.
We propose a new image denoising algorithm, dubbed as Fully Convolutional Adaptive Image DEnoiser (FC-AIDE), that can learn from an offline supervised training set with a fully convolutional neural network as well as adaptively fine-tune the supervised model for each given noisy image. We significantly extend the frame…
We show how a deep denoising autoencoder with lateral connections can be used as an auxiliary unsupervised learning task to support supervised learning. The proposed model is trained to minimize simultaneously the sum of supervised and unsupervised cost functions by back-propagation, avoiding the need for layer-wise pr…
Noise2Inverse removes artifacts in noisy CT images without needing clean data.
L2R learns to denoise images without needing noise distribution knowledge.
We present a representation learning method that learns features at multiple different levels of scale. Working within the unsupervised framework of denoising autoencoders, we observe that when the input is heavily corrupted during training, the network tends to learn coarse-grained features, whereas when the input is …
Paper proposes a self-supervised method to denoise autoregressive signals with heavy-tailed noise.
AugMask trains diffusion models on incomplete tabular data by augmenting missing values and applying denoising supervision.
The study examines denoising and noisy-input regression under distribution shift, revealing double descent behavior and insights for data augmentation.
Transformer model removes noise from light curves efficiently.
This work uses self-supervised learning to generate better labels for financial time-series data.
SidAE combines autoencoders and Siamese networks for self-supervised feature extraction.
New method speeds up image denoising models without sacrificing performance.
DBT combines diffusion models and boosting for supervised learning.
Deep GNNs and self-supervision boost graph learning at scale.
This work studies the denoising of piecewise smooth graph signals that exhibit inhomogeneous levels of smoothness over a graph, where the value at each node can be vector-valued. We extend the graph trend filtering framework to denoising vector-valued graph signals with a family of non-convex regularizers, which exhibi…
We propose a general framework for denoising high-dimensional measurements which requires no prior on the signal, no estimate of the noise, and no clean training data. The only assumption is that the noise exhibits statistical independence across different dimensions of the measurement, while the true signal exhibits s…
Noisy labeled data represent a rich source of information that often are easily accessible and cheap to obtain, but label noise might also have many negative consequences if not accounted for. How to fully utilize noisy labels has been studied extensively within the framework of standard supervised machine learning ove…
This work analyzes how bottleneck layers and skip connections affect linear denoising autoencoders' generalization.
We describe a novel method for training high-quality image denoising models based on unorganized collections of corrupted images. The training does not need access to clean reference images, or explicit pairs of corrupted images, and can thus be applied in situations where such data is unacceptably expensive or impossi…
We present a probabilistic modeling and inference framework for discriminative analysis dictionary learning under a weak supervision setting. Dictionary learning approaches have been widely used for tasks such as low-level signal denoising and restoration as well as high-level classification tasks, which can be applied…
G-SimCLR improves unsupervised learning by clustering images into pseudo labels.
Domain adaptation aims to exploit the knowledge in source domain to promote the learning tasks in target domain, which plays a critical role in real-world applications. Recently, lots of deep learning approaches based on autoencoders have achieved a significance performance in domain adaptation. However, most existing …
Unsupervised method removes satellite noise without paired data.
Recently, the deep-belief-networks (DBN) based voice activity detection (VAD) has been proposed. It is powerful in fusing the advantages of multiple features, and achieves the state-of-the-art performance. However, the deep layers of the DBN-based VAD do not show an apparent superiority to the shallower layers. In this…
Supervised learning based on a deep neural network recently has achieved substantial improvement on speech enhancement. Denoising networks learn mapping from noisy speech to clean one directly, or to a spectrum mask which is the ratio between clean and noisy spectra. In either case, the network is optimized by minimizi…
This work considers noise removal from images, focusing on the well known K-SVD denoising algorithm. This sparsity-based method was proposed in 2006, and for a short while it was considered as state-of-the-art. However, over the years it has been surpassed by other methods, including the recent deep-learning-based newc…
Self-supervised method enhances ultrasound images without needing clean targets.
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…
In recent years, total variation (TV) and Euler's elastica (EE) have been successfully applied to image processing tasks such as denoising and inpainting. This paper investigates how to extend TV and EE to the supervised learning settings on high dimensional data. The supervised learning problem can be formulated as an…
A new distance metric derived from information theory and estimation theory.
Deep neural networks (DNNs) have demonstrated impressive performance on many challenging machine learning tasks. However, DNNs are vulnerable to adversarial inputs generated by adding maliciously crafted perturbations to the benign inputs. As a growing number of attacks have been reported to generate adversarial inputs…
Paper compares optimal denoising methods for generative models, finding different results based on data regularity.
Sparse representations using overcomplete dictionaries have proved to be a powerful tool in many signal processing applications such as denoising, super-resolution, inpainting, compression or classification. The sparsity of the representation very much depends on how well the dictionary is adapted to the data at hand. …
LACD uses unlabeled data to improve conditional diffusion models.
Unified method for simultaneous denoising and clustering.
DDPD separates generation into planning and denoising for improved efficiency.
Problems in machine learning (ML) can involve noisy input data, and ML classification methods have reached limiting accuracies when based on standard ML data sets consisting of feature vectors and their classes. Greater accuracy will require incorporation of prior structural information on data into learning. We study …
Automated quality control for seismic data reduces human labor and time.
We consider the problem of estimating a low-rank matrix from a noisy observed matrix. Previous work has shown that the optimal method depends crucially on the choice of loss function. In this paper, we use a family of weighted loss functions, which arise naturally for problems such as submatrix denoising, denoising wit…
Image denoising is an important pre-processing step in medical image analysis. Different algorithms have been proposed in past three decades with varying denoising performances. More recently, having outperformed all conventional methods, deep learning based models have shown a great promise. These methods are however …