3 papers
cs.CV2023
A Few-Shot Attention Recurrent Residual U-Net for Crack Segmentation
Iason Katsamenis, Eftychios Protopapadakis, Nikolaos Bakalos +3
Recent studies indicate that deep learning plays a crucial role in the automated visual inspection of road infrastructures. However, current learning schemes are static, implying n…
cs.CV2022
Automatic inspection of cultural monuments using deep and tensor-based learning on hyperspectral imagery
Ioannis N. Tzortzis, Ioannis Rallis, Konstantinos Makantasis +3
In Cultural Heritage, hyperspectral images are commonly used since they provide extended information regarding the optical properties of materials. Thus, the processing of such hig…
cs.LG2022
Towards trustworthy Energy Disaggregation: A review of challenges, methods and perspectives for Non-Intrusive Load Monitoring
Maria Kaselimi, Eftychios Protopapadakis, Athanasios Voulodimos +2
Non-intrusive load monitoring (NILM) is the task of disaggregating the total power consumption into its individual sub-components. Over the years, signal processing and machine lea…