Related papers: Dilated Convolutional Neural Networks for Lightwei…

Diacritics restoration is a mandatory step for adequately processing Romanian texts, and not a trivial one, as you generally need context in order to properly restore a character. Most previous methods which were experimented for Romanian…

Recent works indicate that convolutional neural networks (CNN) need large receptive fields (RF) to compete with visual transformers and their attention mechanism. In CNNs, RFs can simply be enlarged by increasing the convolution kernel…

Image denoising is a classical problem in low level computer vision. Model-based optimization methods and deep learning approaches have been the two main strategies for solving the problem. Model-based optimization methods are flexible for…

Convolutional networks for image classification progressively reduce resolution until the image is represented by tiny feature maps in which the spatial structure of the scene is no longer discernible. Such loss of spatial acuity can limit…

Deep neural networks have demonstrated highly competitive performance in super-resolution (SR) for natural images by learning mappings from low-resolution (LR) to high-resolution (HR) images. However, hyperspectral super-resolution remains…

Dense pixel matching problems such as optical flow and disparity estimation are among the most challenging tasks in computer vision. Recently, several deep learning methods designed for these problems have been successful. A sufficiently…

We explore the application of deep residual learning and dilated convolutions to the keyword spotting task, using the recently-released Google Speech Commands Dataset as our benchmark. Our best residual network (ResNet) implementation…

Content-based image retrieval is the process of retrieving a subset of images from an extensive image gallery based on visual contents, such as color, shape or spatial relations, and texture. In some applications, such as localization,…

Deep learning (DL) has shown unprecedented performance for many image analysis and image enhancement tasks. Yet, solving large-scale inverse problems like tomographic reconstruction remains challenging for DL. These problems involve…

Dilated Convolution with Learnable Spacings (DCLS) is a recently proposed variation of the dilated convolution in which the spacings between the non-zero elements in the kernel, or equivalently their positions, are learnable. Non-integer…

In many languages like Arabic, diacritics are used to specify pronunciations as well as meanings. Such diacritics are often omitted in written text, increasing the number of possible pronunciations and meanings for a word. This results in a…

Dilated Convolutions have been shown to be highly useful for the task of image segmentation. By introducing gaps into convolutional filters, they enable the use of larger receptive fields without increasing the original kernel size. Even…

Magnetic resonance imaging (MRI) reconstruction is an active inverse problem which can be addressed by conventional compressed sensing (CS) MRI algorithms that exploit the sparse nature of MRI in an iterative optimization-based manner.…

The use of large pretrained neural networks to create contextualized word embeddings has drastically improved performance on several natural language processing (NLP) tasks. These computationally expensive models have begun to be applied to…

Learning with recurrent neural networks (RNNs) on long sequences is a notoriously difficult task. There are three major challenges: 1) complex dependencies, 2) vanishing and exploding gradients, and 3) efficient parallelization. In this…

Traditional works have shown that patches in a natural image tend to redundantly recur many times inside the image, both within the same scale, as well as across different scales. Make full use of these multi-scale information can improve…

With natural language processing (NLP), researchers aim to enable computers to identify and understand patterns in human languages. This is often difficult because a language embeds many dynamic and varied properties in its syntax,…

Diacritic restoration has gained importance with the growing need for machines to understand written texts. The task is typically modeled as a sequence labeling problem and currently Bidirectional Long Short Term Memory (BiLSTM) models…

This thesis presents and evaluates the Dilated Convolution with Learnable Spacings (DCLS) method. Through various supervised learning experiments in the fields of computer vision, audio, and speech processing, the DCLS method proves to…

Depth prediction plays a key role in understanding a 3D scene. Several techniques have been developed throughout the years, among which Convolutional Neural Network has recently achieved state-of-the-art performance on estimating depth from…