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.
DRSVM uses deep learning to rank relative attributes between image pairs.
Bayesian model improves image completion accuracy by automatically learning low rank structure.
Improved image ranking model using ordinal distance metric learning and multidimensional scaling.
CNNs trained by gradient descent can learn intrinsic image rank robustly to background noises.
New method improves image and signal processing with nonconvex rank surrogates and dual momentum.
Low-rank signal modeling has been widely leveraged to capture non-local correlation in image processing applications. We propose a new method that employs low-rank tensor factor analysis for tensors generated by grouped image patches. The low-rank tensors are fed into the alternative direction multiplier method (ADMM) …
Develops PRPCA for smooth image recovery combining low-rank and smoothness.
New model improves image captioning's ability to describe unseen concepts.
AIR-Net adapts low-rank regularization dynamically for better image completion.
Proposes a new model for image restoration combining deep learning and total variation.
We construct a sequence of primitive-stable representations of free groups into PSL(2,C) whose ranks go to infinity, but whose images are discrete with quotient manifolds that converge geometrically to a knot complement. In particular this implies that the rank and geometry of the image of a primitive-stable representa…
High resolution magnetic resonance (MR) images are desired for accurate diagnostics. In practice, image resolution is restricted by factors like hardware, cost and processing constraints. Recently, deep learning methods have been shown to produce compelling state of the art results for image super-resolution. Paying pa…
Low-rank modeling generally refers to a class of methods that solve problems by representing variables of interest as low-rank matrices. It has achieved great success in various fields including computer vision, data mining, signal processing and bioinformatics. Recently, much progress has been made in theories, algori…
The paper validates a method for recovering over-parameterized matrices and images from noisy measurements.
Paper improves image retrieval quality using nonlinear rank approximations.
The paper analyzes relationships between various image models for restoration.
Proposes a new tensor grid method for image completion.
We optimize rank-based metrics using blackbox differentiation.
A new method classifies color images using quaternion algebra.
Sparsity-based approaches have been popular in many applications in image processing and imaging. Compressed sensing exploits the sparsity of images in a transform domain or dictionary to improve image recovery from undersampled measurements. In the context of inverse problems in dynamic imaging, recent research has de…
New method improves image denoising with fewer parameters and less data.
IRMAE learns compact latent spaces by minimizing rank.
We propose to solve a label ranking problem as a structured output regression task. We adopt a least square surrogate loss approach that solves a supervised learning problem in two steps: the regression step in a well-chosen feature space and the pre-image step. We use specific feature maps/embeddings for ranking data,…
Gradient descent recovers low-rank matrices from corrupted measurements with double over-parameterization.
Medical image reconstruction advances from sparse models to machine learning.
We prove that any action of a higher rank lattice on a Gromov-hyperbolic space is elementary. More precisely, it is either elliptic or parabolic. This is a large generalization of the fact that any action of a higher rank lattice on a tree has a fixed point. A consequence is that any quasi-action of a higher rank latti…
In a plethora of applications dealing with inverse problems, e.g. in image processing, social networks, compressive sensing, biological data processing etc., the signal of interest is known to be structured in several ways at the same time. This premise has recently guided the research to the innovative and meaningful …
Sparsity and low-rank models have been popular for reconstructing images and videos from limited or corrupted measurements. Dictionary or transform learning methods are useful in applications such as denoising, inpainting, and medical image reconstruction. This paper proposes a framework for online (or time-sequential)…
Melanoma is the deadliest form of skin cancer. Computer systems can assist in melanoma detection, but are not widespread in clinical practice. In 2016, an open challenge in classification of dermoscopic images of skin lesions was announced. A training set of 900 images with corresponding class labels and semi-automatic…
Recovering a large matrix from limited measurements is a challenging task arising in many real applications, such as image inpainting, compressive sensing and medical imaging, and this kind of problems are mostly formulated as low-rank matrix approximation problems. Due to the rank operator being non-convex and discont…
Many latent (factorized) models have been proposed for recommendation tasks like collaborative filtering and for ranking tasks like document or image retrieval and annotation. Common to all those methods is that during inference the items are scored independently by their similarity to the query in the latent embedding…
Images seen during test time are often not from the same distribution as images used for learning. This problem, known as domain shift, occurs when training classifiers from object-centric internet image databases and trying to apply them directly to scene understanding tasks. The consequence is often severe performanc…
If is a semisimple Lie group of real rank at least 2 and is an irreducible lattice in , then every homomorphism from to the outer automorphism group of a finitely generated free group has finite image.
SON-NMF estimates nonnegative rank on-the-fly for NMF.
Survey of structured low-rank algorithms for MR signal recovery.
Deep-SLR reduces SLR complexity with CNN, enabling efficient parallel MRI.
Identifies images of determinant morphism for specific co-Higgs bundles.
SoDeep learns approximations of ranking metrics for deep learning tasks.
Proposes a faster Isomap algorithm by reducing eigenvalue decomposition complexity.
Improves tensor networks for classifying medical images.
Algorithm compresses large matrices by approximating them as low rank and low precision factors.
Introduces robust and decomposable AP for image retrieval.
New method estimates neuronal connectivity from partially observed data.
Flow-SSN improves segmentation efficiency and accuracy.
Hashing, or learning binary embeddings of data, is frequently used in nearest neighbor retrieval. In this paper, we develop learning to rank formulations for hashing, aimed at directly optimizing ranking-based evaluation metrics such as Average Precision (AP) and Normalized Discounted Cumulative Gain (NDCG). We first o…
Robust high-dimensional data processing has witnessed an exciting development in recent years, as theoretical results have shown that it is possible using convex programming to optimize data fit to a low-rank component plus a sparse outlier component. This problem is also known as Robust PCA, and it has found applicati…
An LCK manifold with potential is a compact quotient of a Kahler manifold equipped with a positive Kahler potential , such that the monodromy group acts on by holomorphic homotheties and multiplies by a character. The LCK rank is the rank of the image of this character, considered as a function from the …
CANDECOMP/PARAFAC (CP) tensor factorization of incomplete data is a powerful technique for tensor completion through explicitly capturing the multilinear latent factors. The existing CP algorithms require the tensor rank to be manually specified, however, the determination of tensor rank remains a challenging problem e…