Deep learning

Recovering from Catastrophic Receptive Field Overflow in Semantic Segmentation of High Resolution Images: Application to Seabed Characterization

This paper addresses a critical issue in seabed characterization with deep learning semantic segmentation using high-resolution Synthetic Aperture Sonar (SAS) data, that we call Catastrophic Receptive Field Overflow (CRFO). We propose novel methods, …

An end-to-end framework for joint denoising and classification of hyperspectral images

Image denoising and classification are typically conducted separately and sequentially according to their respective objectives. In such a setup, where the two tasks are decoupled, the denoising operation does not optimally serve the classification …

An end-to-end framework for joint denoising and classification of hyperspectral images

Image denoising and classification are typically conducted separately and sequentially according to their respective objectives. In such a setup, where the two tasks are decoupled, the denoising operation does not optimally serve the classification …

From model-based optimization algorithms to deep learning models for clustering hyperspectral images

Hyperspectral images (HSIs), captured by different Earth observation airborne and space-borne systems, provide rich spectral information in hundreds of bands, enabling far better discrimination between ground materials that are often …

Spectral feature fusion networks with dual attention for hyperspectral image classification

Recent progress in spectral classification is largely attributed to the use of convolutional neural networks (CNN). While a variety of successful architectures have been proposed, they all extract spectral features from various portions of adjacent …

Spectral feature fusion networks with dual attention for hyperspectral image classification

Recent progress in spectral classification is largely attributed to the use of convolutional neural networks (CNN). While a variety of successful architectures have been proposed, they all extract spectral features from various portions of adjacent …

Virtual restoration of paintings based on deep learning

Over time, crack pattern (craquelure) inevitably develops in paintings as a sign of their ageing, sometimes accompanied by larger losses of paint (lacunas). In restoration treatments, cracks are typically not filled in, and virtual restoration is …

A deep learning-based approach for defect detection and removing on archival photos

Many archival photos are unique, existed only in a single copy. Some of them are damaged due to improper archiving (e.g. affected by direct sunlight, humidity, insects, etc.) or have physical damage resulting in the appearance of cracks, scratches on …

Deep learning for paint loss detection with a multiscale, translation invariant network

We explore the potential of deep learning in digital painting analysis to facilitate condition reporting and to support restoration treatments. We address the problem of paint loss detection and develop a multiscale deep learning system with dilated …