Search Results for author:
Found 10 papers, 0 papers with code
U-Sketch: An Efficient Approach for Sketch to Image Diffusion Models
Diffusion models have demonstrated remarkable performance in text-to-image synthesis, producing realistic and high resolution images that faithfully adhere to the corresponding text-prompts.
Mitigating Exposure Bias in Discriminator Guided Diffusion Models
Diffusion Models have demonstrated remarkable performance in image generation.
A Few-Shot Attention Recurrent Residual U-Net for Crack Segmentation
Recent studies indicate that deep learning plays a crucial role in the automated visual inspection of road infrastructures.
Towards trustworthy Energy Disaggregation: A review of challenges, methods and perspectives for Non-Intrusive Load Monitoring
Non-intrusive load monitoring (NILM) is the task of disaggregating the total power consumption into its individual sub-components.
Automatic inspection of cultural monuments using deep and tensor-based learning on hyperspectral imagery
In Cultural Heritage, hyperspectral images are commonly used since they provide extended information regarding the optical properties of materials.
Rank-R FNN: A Tensor-Based Learning Model for High-Order Data Classification
We hereby propose the Rank-R Feedforward Neural Network (FNN), a tensor-based nonlinear learning model that imposes Canonical/Polyadic decomposition on its parameters, thereby offering two core advantages compared to typical machine learning methods.
Pixel-level Corrosion Detection on Metal Constructions by Fusion of Deep Learning Semantic and Contour Segmentation
Corrosion detection on metal constructions is a major challenge in civil engineering for quick, safe and effective inspection.
Space-Time Domain Tensor Neural Networks: An Application on Human Pose Classification
Recent advances in sensing technologies require the design and development of pattern recognition models capable of processing spatiotemporal data efficiently.
Common Mode Patterns for Supervised Tensor Subspace Learning
In this work we propose a method for reducing the dimensionality of tensor objects in a binary classification framework.
Tensor-based Nonlinear Classifier for High-Order Data Analysis
We also introduce a new learning algorithm to train the model, and we evaluate the \textit{Rank}-1 FNN on third-order hyperspectral data.
