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.
A deep learning system classifies hyperspectral images using denoising autoencoders and pixel mixtures.
In blind hyperspectral unmixing (HU), the pure-pixel assumption is well-known to be powerful in enabling simple and effective blind HU solutions. However, the pure-pixel assumption is not always satisfied in an exact sense, especially for scenarios where pixels are heavily mixed. In the no pure-pixel case, a good blind…
Blind source separation is a common processing tool to analyse the constitution of pixels of hyperspectral images. Such methods usually suppose that pure pixel spectra (endmembers) are the same in all the image for each class of materials. In the framework of remote sensing, such an assumption is no more valid in the p…
InstaHide encrypts images for privacy in distributed learning.
Deep learning predicts semitransparent pigment mixtures for novice painters.
Imaging spectrometers measure electromagnetic energy scattered in their instantaneous field view in hundreds or thousands of spectral channels with higher spectral resolution than multispectral cameras. Imaging spectrometers are therefore often referred to as hyperspectral cameras (HSCs). Higher spectral resolution ena…
NICE framework explains CNN predictions and compresses images.
New method recovers causal DAGs from general environments without strict assumptions.
In this paper, we study the nonnegative matrix factorization problem under the separability assumption (that is, there exists a cone spanned by a small subset of the columns of the input nonnegative data matrix containing all columns), which is equivalent to the hyperspectral unmixing problem under the linear mixing mo…
Spectral variability is one of the major issue when conducting hyperspectral unmixing. Within a given image composed of some elementary materials (herein referred to as endmember classes), the spectral signature characterizing these classes may spatially vary due to intrinsic component fluctuations or external factors …
Any subset of the plane can be approximated by a set of square pixels. This transition from a shape to its pixelation is rather brutal since it destroys geometric and topological information about the shape. Using a technique inspired by Morse Theory, we algorithmically produce a PL approximation of the original shape …
SemGANs generate pixel-level accurate semantic images.
We develop a method for user-controllable semantic image inpainting: Given an arbitrary set of observed pixels, the unobserved pixels can be imputed in a user-controllable range of possibilities, each of which is semantically coherent and locally consistent with the observed pixels. We achieve this using a deep generat…
Deep learning improves PS pixel selection in SAR interferometry.
SaliencyMix augments images with salient patches to improve model generalization.
New method uses image-level and pixel-level annotations for brain tumor segmentation.
Pixel-space diffusion models outperform latent models on high-resolution image synthesis.
One pixel can significantly alter deep neural network outputs, revealing propagation patterns and vulnerability hotspots.
Improves spline quality and accuracy in computational microscopy.
A new method for adversarial attacks using physical parameters like lighting and geometry.
Evolutionary algorithm finds optimal pixel perturbations to improve neural network generalization.
ALIEN detects multiple small objects and estimates their pixel locations and features.
Probabilistic inpainting learns multiple plausible images from missing data.
Study shows various pixel p-norm measures do not match human perception of adversarial attacks.
DEceit constructs effective universal pixel-restricted perturbations for deep image classifiers.
Simple image augmentation boosts deep RL from pixels.
Pixel-wise classification, where each pixel is assigned to a predefined class, is one of the most important procedures in hyperspectral image (HSI) analysis. By representing a test pixel as a linear combination of a small subset of labeled pixels, a sparse representation classifier (SRC) gives rather plausible results …
SRTC model for background/foreground separation with missing pixels.
This paper proposes an innovative method for segmentation of skin lesions in dermoscopy images developed by the authors, based on fuzzy classification of pixels and histogram thresholding.
New NAM model improves image processing speed and accuracy.
New method certifies robustness to sparse adversarial attacks.
Data-efficient reinforcement learning (RL) in continuous state-action spaces using very high-dimensional observations remains a key challenge in developing fully autonomous systems. We consider a particularly important instance of this challenge, the pixels-to-torques problem, where an RL agent learns a closed-loop con…
VAEBM combines VAEs and EBMs for efficient image generation.
Data-efficient learning in continuous state-action spaces using very high-dimensional observations remains a key challenge in developing fully autonomous systems. In this paper, we consider one instance of this challenge, the pixels to torques problem, where an agent must learn a closed-loop control policy from pixel i…
This paper considers a recently emerged hyperspectral unmixing formulation based on sparse regression of a self-dictionary multiple measurement vector (SD-MMV) model, wherein the measured hyperspectral pixels are used as the dictionary. Operating under the pure pixel assumption, this SD-MMV formalism is special in that…
PixelCNNs are a recently proposed class of powerful generative models with tractable likelihood. Here we discuss our implementation of PixelCNNs which we make available at https://github.com/openai/pixel-cnn. Our implementation contains a number of modifications to the original model that both simplify its structure an…
BriarPatches obscure sensitive attributes to achieve demographic parity.
Scene understanding remains a significant challenge in the computer vision community. The visual psychophysics literature has demonstrated the importance of interdependence among parts of the scene. Yet, the majority of methods in computer vision remain local. Pictorial structures have arisen as a fundamental parts-bas…
Randomly dropping pixels improves neural network robustness.
Pixle attacks images by rearranging pixels, bypassing neural networks.
Wide adoption of artificial neural networks in various domains has led to an increasing interest in defending adversarial attacks against them. Preprocessing defense methods such as pixel discretization are particularly attractive in practice due to their simplicity, low computational overhead, and applicability to var…
We propose a novel approach for pixel classification in hyperspectral images, leveraging on both the spatial and spectral information in the data. The introduced method relies on a recently proposed framework for learning on distributions -- by representing them with mean elements in reproducing kernel Hilbert spaces (…
One pixel modification can make deep models unlearnable.
We describe an algorithm that associates to each positive real number and each finite collection of planar pixels of size a planar piecewise linear set with the following additional property: if is the collection of pixels of size that touch a given compact semialgebraic set , then the …
Semantic boundary and edge detection aims at simultaneously detecting object edge pixels in images and assigning class labels to them. Systematic training of predictors for this task requires the labeling of edges in images which is a particularly tedious task. We propose a novel strategy for solving this task, when pi…
A deep model learns to infer fluorescence labels from unlabeled microscopy images.
A new framework uses pixel-based images for realistic cloth animations.
A novel tracking method for dense honeybee colonies using pixel personality.