Related papers: Iterative Patch Selection for High-Resolution Imag…
Classifying large images with small or tiny regions of interest (ROI) is challenging due to computational and memory constraints. Weakly supervised memory-efficient patch selectors have achieved results comparable with strongly supervised…
Neural Networks require large amounts of memory and compute to process high resolution images, even when only a small part of the image is actually informative for the task at hand. We propose a method based on a differentiable Top-K…
Multi-focus image fusion aims to combine multiple partially focused images into a single all-in-focus image. Although deep learning has shown promise in this task, its effectiveness is often limited by the scarcity of suitable training…
Despite the rapid advancement in the field of image recognition, the processing of high-resolution imagery remains a computational challenge. However, this processing is pivotal for extracting detailed object insights in areas ranging from…
Attention-based models are proliferating in the space of image analytics, including segmentation. The standard method of feeding images to transformer encoders is to divide the images into patches and then feed the patches to the model as a…
Recent advances in deep learning have shown exciting promise in filling large holes in natural images with semantically plausible and context aware details, impacting fundamental image manipulation tasks such as object removal. While these…
Edge-preserving image smoothing is a fundamental procedure for many computer vision and graphic applications. There is a tradeoff between the smoothing quality and the processing speed: the high smoothing quality usually requires a high…
Existing deep architectures cannot operate on very large signals such as megapixel images due to computational and memory constraints. To tackle this limitation, we propose a fully differentiable end-to-end trainable model that samples and…
Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. However, prevailing SR models suffer from prohibitive memory footprint and intensive computations, which limits further…
With the continuous improvement of device imaging resolution, the popularity of Ultra-High-Definition (UHD) images is increasing. Unfortunately, existing methods for fusing multi-exposure images in dynamic scenes are designed for…
Transformer-based architectures start to emerge in single image super resolution (SISR) and have achieved promising performance. Most existing Vision Transformers divide images into the same number of patches with a fixed size, which may…
The goal of data selection is to capture the most structural information from a set of data. This paper presents a fast and accurate data selection method, in which the selected samples are optimized to span the subspace of all data. We…
Computational analysis of whole slide images (WSIs) has seen significant research progress in recent years, with applications ranging across important diagnostic and prognostic tasks such as survival or cancer subtype prediction. Many…
Existing self-supervised learning methods based on contrastive learning and masked image modeling have demonstrated impressive performances. However, current masked image modeling methods are mainly utilized in natural images, and their…
Meta learning approaches to few-shot classification are computationally efficient at test time, requiring just a few optimization steps or single forward pass to learn a new task, but they remain highly memory-intensive to train. This…
While diffusion models significantly improve the perceptual quality of super-resolved images, they usually require a large number of sampling steps, resulting in high computational costs and long inference times. Recent efforts have…
Series photo selection (SPS) is an important branch of the image aesthetics quality assessment, which focuses on finding the best one from a series of nearly identical photos. While a great progress has been observed, most of the existing…
Deep neural network models used for medical image segmentation are large because they are trained with high-resolution three-dimensional (3D) images. Graphics processing units (GPUs) are widely used to accelerate the trainings. However, the…
Histopathological image analysis is an essential process for the discovery of diseases such as cancer. However, it is challenging to train CNN on whole slide images (WSIs) of gigapixel resolution considering the available memory capacity.…
Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of…