Related papers: Multi-Scale Spatially-Asymmetric Recalibration for…

Remote sensing image retrieval (RSIR) is the process of ranking database images depending on the degree of similarity compared to the query image. As the complexity of RSIR increases due to the diversity in shooting range, angle, and…

Multispectral imaging (MSI) plays a critical role in material classification, environmental monitoring, and remote sensing. However, MSI sensors typically have wavelength-dependent resolution, which limits downstream analysis. MSI…

Although image restoration has advanced significantly, most existing methods target only a single type of degradation. In real-world scenarios, images often contain multiple degradations simultaneously, such as rain, noise, and haze,…

LiDAR point-cloud segmentation is an important problem for many applications. For large-scale point cloud segmentation, the \textit{de facto} method is to project a 3D point cloud to get a 2D LiDAR image and use convolutions to process it.…

Magnetic resonance imaging (MRI) is a valuable clinical tool for displaying anatomical structures and aiding in accurate diagnosis. Medical image super-resolution (SR) reconstruction using deep learning techniques can enhance lesion…

Object classification in synthetic aperture sonar (SAS) imagery is usually a data starved and class imbalanced problem. There are few objects of interest present among much benign seafloor. Despite these problems, current classification…

In this paper we investigate the use of discriminative model learning through Convolutional Neural Networks (CNNs) for SAR image despeckling. The network uses a residual learning strategy, hence it does not recover the filtered image, but…

Convolutional neural networks (CNNs) have shown dramatic improvements in single image super-resolution (SISR) by using large-scale external samples. Despite their remarkable performance based on the external dataset, they cannot exploit…

In recent years, Contrastive Language-Image Pretraining (CLIP) has been widely applied to Weakly Supervised Semantic Segmentation (WSSS) tasks due to its powerful cross-modal semantic understanding capabilities. This paper proposes a novel…

Single Image Super-Resolution (SISR) task refers to learn a mapping from low-resolution images to the corresponding high-resolution ones. This task is known to be extremely difficult since it is an ill-posed problem. Recently, Convolutional…

The widespread success of convolutional neural networks may largely be attributed to their intrinsic property of translation equivariance. However, convolutions are not equivariant to variations in scale and fail to generalize to objects of…

Because hyperspectral remote sensing images contain a lot of redundant information and the data structure is highly non-linear, leading to low classification accuracy of traditional machine learning methods. The latest research shows that…

With the increasing availability of optical and synthetic aperture radar (SAR) images thanks to the Sentinel constellation, and the explosion of deep learning, new methods have emerged in recent years to tackle the reconstruction of optical…

The primary aim of this manuscript is to underscore a significant limitation in current deep learning models, particularly vision models. Unlike human vision, which efficiently selects only the essential visual areas for further processing,…

We propose a supervised machine learning approach for boosting existing signal and image recovery methods and demonstrate its efficacy on example of image reconstruction in computed tomography. Our technique is based on a local nonlinear…

Convolutional Neural Networks (CNNs) require large image corpora to be trained on classification tasks. The variation in image resolutions, sizes of objects and patterns depicted, and image scales, hampers CNN training and performance,…

Unsupervised learning algorithms are beginning to achieve accuracies comparable to their supervised counterparts on benchmark computer vision tasks, but their utility for practical applications has not yet been demonstrated. In this work,…

Supervised classification and representation learning are two widely used classes of methods to analyze multivariate images. Although complementary, these methods have been scarcely considered jointly in a hierarchical modeling. In this…

MLP-based architectures, which consist of a sequence of consecutive multi-layer perceptron blocks, have recently been found to reach comparable results to convolutional and transformer-based methods. However, most adopt spatial MLPs which…

Image harmonization is an important step in photo editing to achieve visual consistency in composite images by adjusting the appearances of foreground to make it compatible with background. Previous approaches to harmonize composites are…