Related papers: Corrigendum to "Random grid-based visual secret sh…

Image smoothing is a fundamental low-level vision task that aims to preserve salient structures of an image while removing insignificant details. Deep learning has been explored in image smoothing to deal with the complex entanglement of…

Weakly supervised object detection (WSOD) aims at learning precise object detectors with only image-level tags. In spite of intensive research on deep learning (DL) approaches over the past few years, there is still a significant…

Self-supervised learning (SSL) is one strategy for addressing the paucity of labelled data in medical imaging by learning representations from unlabelled images. Contrastive and non-contrastive SSL methods produce learned representations…

Contrastive learning methods train visual encoders by comparing views from one instance to others. Typically, the views created from one instance are set as positive, while views from other instances are negative. This binary instance…

This paper explores the use of contrastive learning and generative adversarial networks for generating realistic underwater images from synthetic images with uniform lighting. We investigate the performance of image translation models for…

Texture classification is a pivotal task in computer vision, presenting unique challenges due to high inter-class similarity and the sensitivity of structural patterns to scale and illumination changes. While Convolutional Neural Networks…

Recently, an image encryption scheme based on chaotic standard and logistic maps was proposed by Patidar et al. It was later reported by Rhouma et al. that an equivalent secret key can be reconstructed with only one known/chosen-plaintext…

Attributed graph clustering, which learns node representation from node attribute and topological graph for clustering, is a fundamental but challenging task for graph analysis. Recently, methods based on graph contrastive learning (GCL)…

Contrastive self-supervised learning (CSL) has managed to match or surpass the performance of supervised learning in image and video classification. However, it is still largely unknown if the nature of the representations induced by the…

In this work, we present new calculations of the observables associated with synthetic metal and HI absorption lines in the spectra of high redshift quasars, inspired by questions and limitations raised in work with a uniform Haardt-Madau…

This paper is concerned with the construction of high order schemes on irregular grids for balance laws, including a discussion of an a-posteriori error indicator based on the numerical entropy production. We also impose well-balancing on…

Self-Supervised Learning (SSL) methods operate on unlabeled data to learn robust representations useful for downstream tasks. Most SSL methods rely on augmentations obtained by transforming the 2D image pixel map. These augmentations ignore…

Recent research advances have revealed the computational secrecy of the compressed sensing (CS) paradigm. Perfect secrecy can also be achieved by normalizing the CS measurement vector. However, these findings are established on real…

Contrastive learning is a powerful technique to learn representations that are semantically distinctive and geometrically invariant. While most of the earlier approaches have demonstrated its effectiveness on single-modality learning tasks…

Reliable detection of out-of-distribution (OOD) inputs is increasingly understood to be a precondition for deployment of machine learning systems. This paper proposes and investigates the use of contrastive training to boost OOD detection…

Learning a powerful representation from point clouds is a fundamental and challenging problem in the field of computer vision. Different from images where RGB pixels are stored in the regular grid, for point clouds, the underlying semantic…

In this short paper we prove that the sum of the squares of negative (or positive) eigenvalues of the adjacency matrix of a graph is lower bounded by the sum of the degrees divided by the vector chromatic number, resolving a conjecture by…

We study the encryption and decryption processes of color images using the synchronization of polarization dynamics in a free-running vertical-cavity surface-emitting laser (VCSEL). Here, we consider a bidirectional master-slave…

This paper gives a new scheme of colour image compression related to singular values matrix approximation. The image has to be converted in luminance / chrominance space before being processed like JPEG standard 4 : 2 : 0. Our approach is…

There exists a widely accepted set of assertions in the digital image and video coding literature, which are as follows: the Human Visual System (HVS) is more sensitive to luminance (often confused with brightness) than photon energies…