Related papers: Shape-Dependent, Deep-Learning-Assisted Metamateri…
A common heuristic in semi-supervised deep learning (SSDL) is to select unlabelled data based on a notion of semantic similarity to the labelled data. For example, labelled images of numbers should be paired with unlabelled images of…
We approach self-supervised learning of image representations from a statistical dependence perspective, proposing Self-Supervised Learning with the Hilbert-Schmidt Independence Criterion (SSL-HSIC). SSL-HSIC maximizes dependence between…
The possibility of spatially resolving the optical properties of atomically thin materials is especially appealing as they can be modulated at the micro- and nanoscale by reducing their thickness, changing the doping level or applying a…
Self-supervised learning (SSL) has gained widespread attention in the remote sensing (RS) and earth observation (EO) communities owing to its ability to learn task-agnostic representations without human-annotated labels. Nevertheless, most…
We propose a new method for integrating metasurfaces in optical design using semi-analytical modelling of dielectric nanostructures. The latter computes the output phase of an electric field incident on the metasurface, allowing their use…
With the fast growth in the visual surveillance and security sectors, thermal infrared images have become increasingly necessary ina large variety of industrial applications. This is true even though IR sensors are still more expensive than…
The performance of deep learning models in remote sensing (RS) strongly depends on the availability of high-quality labeled data. However, collecting large-scale annotations is costly and time-consuming, while vast amounts of unlabeled…
Multi-image super-resolution (MISR) allows to increase the spatial resolution of a low-resolution (LR) acquisition by combining multiple images carrying complementary information in the form of sub-pixel offsets in the scene sampling, and…
Learning robust and scalable visual representations from massive multi-view video data remains a challenge in computer vision and autonomous driving. Existing pre-training methods either rely on expensive supervised learning with 3D…
Recent advances in meta-optics have enabled diverse functionalities in compact optical devices; however, conventional forward design approaches become inadequate as device complexity and scale grow. Inverse design offers a powerful…
With the advent of microsphere assisted microscopy in 2011, this technique emerged as a simple and easy way to obtain optical super-resolution. Although the possible mechanisms of imaging by microspheres are debated in the literature, most…
Most of existing manifold learning methods rely on Mean Squared Error (MSE) or $\ell_2$ norm. However, for the problem of image quality assessment, these are not promising measure. In this paper, we introduce the concept of an image…
Deeper convolutional neural networks provide more capacity to approximate complex mapping functions. However, increasing network depth imposes difficulties on training and increases model complexity. This paper presents a new nonlinear…
Salient object detection (SOD), which aims to find the most important region of interest and segment the relevant object/item in that area, is an important yet challenging vision task. This problem is inspired by the fact that human seems…
Two-dimensional (2D) in-plane heterostructures including compositionally graded alloys and lateral heterostructures with defined interfaces display rich optoelectronic properties and offer versatile platforms to explore one-dimensional…
We propose a novel semi-supervised active learning (SSAL) framework for monocular 3D object detection with LiDAR guidance (MonoLiG), which leverages all modalities of collected data during model development. We utilize LiDAR to guide the…
Deep Learning could drastically boost the classification accuracy for Hyperspectral Imaging (HSI). Still, the training on the mostly small hyperspectral data sets is not trivial. Two key challenges are the large channel dimension of the…
Controlling defects in semiconductor processes is important for maintaining yield, improving production cost, and preventing time-dependent critical component failures. Electron beam-based imaging has been used as a tool to survey wafers in…
Training deep learning models for three-dimensional (3D) medical imaging, such as Computed Tomography (CT), is fundamentally challenged by the scarcity of labeled data. While pre-training on natural images is common, it results in a…
Content-based image retrieval (CBIR) with self-supervised learning (SSL) accelerates clinicians' interpretation of similar images without manual annotations. We develop a CBIR from the contrastive learning SimCLR and incorporate a…