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.
Face recognition systems are vulnerable to composite face reconstruction attacks.
Optimizes master faces for 2D and 3D face verification using evolutionary algorithms and neural networks.
The paper proves a Minkowski-like theorem for tetrahedra in dS3 and AdS3.
We present a generative autoencoder that provides fast encoding, faithful reconstructions (eg. retaining the identity of a face), sharp generated/reconstructed samples in high resolutions, and a well-structured latent space that supports semantic manipulation of the inputs. There are no current autoencoder or GAN model…
State of the art deep generative networks are capable of producing images with such incredible realism that they can be suspected of memorizing training images. It is why it is not uncommon to include visualizations of training set nearest neighbors, to suggest generated images are not simply memorized. We demonstrate …
In this paper, we address the problem of data reconstruction from privacy-protected templates, based on recent concept of sparse ternary coding with ambiguization (STCA). The STCA is a generalization of randomization techniques which includes random projections, lossy quantization, and addition of ambiguization noise t…
Humans are able to imagine a person's voice from the person's appearance and imagine the person's appearance from his/her voice. In this paper, we make the first attempt to develop a method that can convert speech into a voice that matches an input face image and generate a face image that matches the voice of the inpu…
We present a generalization of Minkowski's classic theorem on the reconstruction of tetrahedra from algebraic data to homogeneously curved spaces. Euclidean notions such as the normal vector to a face are replaced by Levi-Civita holonomies around each of the tetrahedron's faces. This allows the reconstruction of both s…
Enhances 2D face recognition with 3D features using active illumination.
Here, we present a novel approach to solve the problem of reconstructing perceived stimuli from brain responses by combining probabilistic inference with deep learning. Our approach first inverts the linear transformation from latent features to brain responses with maximum a posteriori estimation and then inverts the …
This paper is the first work to propose a network to predict a structured uncertainty distribution for a synthesized image. Previous approaches have been mostly limited to predicting diagonal covariance matrices. Our novel model learns to predict a full Gaussian covariance matrix for each reconstruction, which permits …
Unsupervised image inpainting models generate plausible reconstructions from incomplete data.
Extends L2-norm LDA to 2D inputs using Bhattacharyya bound.
A novel method for feature selection using a reparameterized logitNormal distribution.
We investigate discrete groups of isometries of a complete connected Riemannian manifold which are generated by reflections, in particular those generated by disecting reflections. We show that these are Coxeter groups, and that the the orbit space is isometric to a Weyl chamber which is a Riemannian …
Generative model learns to autoencode and generate sets of images.
PolyGen models 3D meshes directly, predicting vertices and faces sequentially.
Reconstruct trapezoidal surfaces from point clouds.
This paper proposes a new evaluation metric and boosting method for weight separability in neural network design. In contrast to general visual recognition methods designed to encourage both intra-class compactness and inter-class separability of latent features, we focus on estimating linear independence of column vec…
Powerful generative adversarial networks (GAN) have been developed to automatically synthesize realistic images from text. However, most existing tasks are limited to generating simple images such as flowers from captions. In this work, we extend this problem to the less addressed domain of face generation from fine-gr…
DefenseVGAE defends graph neural networks against adversarial attacks.
Bidirectional VAE reduces parameters and improves image tasks.
We present a definition of discrete channel surfaces in Lie sphere geometry, which reflects several properties for smooth channel surfaces. Various sets of data, defined at vertices, on edges or on faces, are associated with a discrete channel surface that may be used to reconstruct the underlying particular discrete L…
This is a detailed tutorial paper which explains the Principal Component Analysis (PCA), Supervised PCA (SPCA), kernel PCA, and kernel SPCA. We start with projection, PCA with eigen-decomposition, PCA with one and multiple projection directions, properties of the projection matrix, reconstruction error minimization, an…
New attack recovers user-level information from large batch images.
A new method learns dynamic graph representations from time-varying data.
Dictionary learning algorithms have been successfully used for both reconstructive and discriminative tasks, where an input signal is represented with a sparse linear combination of dictionary atoms. While these methods are mostly developed for single-modality scenarios, recent studies have demonstrated the advantages …
Proposes AEGAN for stable GAN training.
The field of multiple view geometry has seen tremendous progress in reconstruction and calibration due to methods for extracting reliable point features and key developments in projective geometry. Point features, however, are not available in certain applications and result in unstructured point cloud reconstructions.…
Bayesian image reconstruction using pre-trained generative models.
This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have raised serious concerns given that training data usually contain privacy-sensitive information. Thus far, successful model-inversion attacks …
CSGM framework applied to clinical MRI data for robust reconstructions.
One of the most important problems of data processing in high energy and nuclear physics is the event reconstruction. Its main part is the track reconstruction procedure which consists in looking for all tracks that elementary particles leave when they pass through a detector among a huge number of points, so-called hi…
A novel approach stores encoded images as centroids and covariance matrices to improve classification accuracy with less memory.
TadGAN detects anomalies in time series data using GANs and LSTM.
Deep neural networks have presented impressive performance in biometric applications. However, their performance is highly at risk when facing carefully crafted input samples known as adversarial examples. In this paper, we present three defense strategies to detect adversarial iris examples. These defense strategies a…
SentenceMIM learns rich latent representations for variable-length language data.
Study improves confidence measures in medical imaging pipelines by addressing bias.
New methods improve feature extraction and representation quality in supervised and unsupervised DR.
PTOPOFL uses topological descriptors to protect privacy in federated learning.
We present an autoencoder that leverages learned representations to better measure similarities in data space. By combining a variational autoencoder with a generative adversarial network we can use learned feature representations in the GAN discriminator as basis for the VAE reconstruction objective. Thereby, we repla…
Study finds no significant short-term impact on liquidity supply after protocol fees were reduced.
Gaussian processes are a flexible Bayesian nonparametric modelling approach that has been widely applied but poses computational challenges. To address the poor scaling of exact inference methods, approximation methods based on sparse Gaussian processes (SGP) are attractive. An issue faced by SGP, especially in latent …
Facial attribute editing aims to manipulate single or multiple attributes of a face image, i.e., to generate a new face with desired attributes while preserving other details. Recently, generative adversarial net (GAN) and encoder-decoder architecture are usually incorporated to handle this task with promising results.…
A neural network learns phase space properties for time series analysis.
Machine learning algorithms are typically run on large scale, distributed compute infrastructure that routinely face a number of unavailabilities such as failures and temporary slowdowns. Adding redundant computations using coding-theoretic tools called "codes" is an emerging technique to alleviate the adverse effects …
In the field of machine learning, it is still a critical issue to identify and supervise the learned representation without manually intervening or intuition assistance to extract useful knowledge or serve for the downstream tasks. In this work, we focus on supervising the influential factors extracted by the variation…
In many scientific disciplines structures in high-dimensional data have to be found, e.g., in stellar spectra, in genome data, or in face recognition tasks. In this work we present a novel approach to non-linear dimensionality reduction. It is based on fitting K-nearest neighbor regression to the unsupervised regressio…