Related papers: MaskBlur: Spatial and Angular Data Augmentation fo…

Data augmentation is an effective way to improve the performance of deep networks. Unfortunately, current methods are mostly developed for high-level vision tasks (e.g., classification) and few are studied for low-level vision tasks (e.g.,…

Medical image super-resolution (SR) is an active research area that has many potential applications, including reducing scan time, bettering visual understanding, increasing robustness in downstream tasks, etc. However, applying…

Self-supervised learning (SSL) has potential for effective representation learning in medical imaging, but the choice of data augmentation is critical and domain-specific. It remains uncertain if general augmentation policies suit surgical…

Deep neural networks are capable of learning powerful representations to tackle complex vision tasks but expose undesirable properties like the over-fitting issue. To this end, regularization techniques like image augmentation are necessary…

Deep neural networks have emerged as very successful tools for image restoration and reconstruction tasks. These networks are often trained end-to-end to directly reconstruct an image from a noisy or corrupted measurement of that image. To…

Deep learning (DL) algorithms have shown significant performance in various computer vision tasks. However, having limited labelled data lead to a network overfitting problem, where network performance is bad on unseen data as compared to…

Deep learning models have achieved remarkable success in computer vision but still rely heavily on large-scale labeled data and tend to overfit when data is limited or distributions shift. Data augmentation -- particularly mask-based…

Light field imaging extends the traditional photography by capturing both spatial and angular distribution of light, which enables new capabilities, including post-capture refocusing, post-capture aperture control, and depth estimation from…

Domain shift is a well-known problem in the medical imaging community. In particular, for endoscopic image analysis where the data can have different modalities the performance of deep learning (DL) methods gets adversely affected. In other…

Accurate and consistent construction of point clouds from LiDAR scanning data is fundamental for 3D modeling applications. Current solutions, such as multiview point cloud registration and LiDAR bundle adjustment, predominantly depend on…

Deep learning has recently gained attention in the atmospheric and oceanic sciences for its potential to improve the accuracy of numerical simulations or to reduce computational costs. Super-resolution is one such technique for…

Most single image super-resolution (SR) methods are developed on synthetic low-resolution (LR) and high-resolution (HR) image pairs, which are simulated by a predetermined degradation operation, e.g., bicubic downsampling. However, these…

Deep learning techniques for medical image analysis usually suffer from the domain shift between source and target data. Most existing works focus on unsupervised domain adaptation (UDA). However, in practical applications, privacy issues…

This study introduces a novel data augmentation technique, ADLDA, aimed at mitigating the negative impact of data distribution shifts caused by the data augmentation process in computer vision task. ADLDA partitions augmented data into…

Image deblurring aims to remove undesired blurs from an image captured in a dynamic scene. Much research has been dedicated to improving deblurring performance through model architectural designs. However, there is little work on data…

An unsupervised framework for hyperspectral image (HSI) clustering is proposed that incorporates masked deep representation learning with diffusion-based clustering, extending the Spatially-Regularized Superpixel-based Diffusion Learning…

Data augmentation (DA) plays a critical role in improving the generalization of deep learning models. Recent works on automatically searching for DA policies from data have achieved great success. However, existing automated DA methods…

Diffusion magnetic resonance imaging (dMRI) often suffers from low spatial and angular resolution due to inherent limitations in imaging hardware and system noise, adversely affecting the accurate estimation of microstructural parameters…

We investigate the efficacy of data augmentations to close the domain gap in spaceborne computer vision, crucial for autonomous operations like on-orbit servicing. As the use of computer vision in space increases, challenges such as hostile…

Pre-trained diffusion models utilized for image generation encapsulate a substantial reservoir of a priori knowledge pertaining to intricate textures. Harnessing the potential of leveraging this a priori knowledge in the context of image…