Related papers: Patch-Based Stochastic Attention for Image Editing

We propose an enhanced deep learning-based model for image segmentation of the left and right ventricles and myocardium scar tissue from cardiac magnetic resonance (CMR) images. The proposed technique integrates UNet, channel and spatial…

A new multi-attention based method for solving the MIL problem (MAMIL), which takes into account the neighboring patches or instances of each analyzed patch in a bag, is proposed. In the method, one of the attention modules takes into…

Can we leverage high-resolution information without the unsustainable quadratic complexity to input scale? We propose Traversal Network (TNet), a novel multi-scale hard-attention architecture, which traverses image scale-space in a top-down…

Patch-level image representation is very important for object classification and detection, since it is robust to spatial transformation, scale variation, and cluttered background. Many existing methods usually require fine-grained…

While fine-tuning pre-trained networks has become a popular way to train image segmentation models, such backbone networks for image segmentation are frequently pre-trained using image classification source datasets, e.g., ImageNet. Though…

Image composition is one of the most important applications in image processing. However, the inharmonious appearance between the spliced region and background degrade the quality of the image. Thus, we address the problem of Image…

Tools to analyze the latent space of deep neural networks provide a step towards better understanding them. In this work, we motivate sparse subspace clustering (SSC) with an aim to learn affinity graphs from the latent structure of a given…

Classifying large-scale image data into object categories is an important problem that has received increasing research attention. Given the huge amount of data, non-parametric approaches such as nearest neighbor classifiers have shown…

Effective shadow removal is pivotal in enhancing the visual quality of images in various applications, ranging from computer vision to digital photography. During the last decades physics and machine learning -based methodologies have been…

In recent years, employing layer attention to enhance interaction among hierarchical layers has proven to be a significant advancement in building network structures. In this paper, we delve into the distinction between layer attention and…

Graph representation learning has rapidly emerged as a pivotal field of study. Despite its growing popularity, the majority of research has been confined to embedding single-layer graphs, which fall short in representing complex systems…

Deep representation learning is a crucial procedure in multimedia analysis and attracts increasing attention. Most of the popular techniques rely on convolutional neural network and require a large amount of labeled data in the training…

Traditional CNN models are trained and tested on relatively low resolution images (<300 px), and cannot be directly operated on large-scale images due to compute and memory constraints. We propose Patch Gradient Descent (PatchGD), an…

The captured images under low light conditions often suffer insufficient brightness and notorious noise. Hence, low-light image enhancement is a key challenging task in computer vision. A variety of methods have been proposed for this task,…

Semi-supervised learning (SSL), which aims at leveraging a few labeled images and a large number of unlabeled images for network training, is beneficial for relieving the burden of data annotation in medical image segmentation. According to…

Deep learning methods such as convolutional neural networks (CNNs) are difficult to directly utilize to analyze whole slide images (WSIs) due to the large image dimensions. We overcome this limitation by proposing a novel two-stage…

The deep learning technique was used to increase the performance of single image super-resolution (SISR). However, most existing CNN-based SISR approaches primarily focus on establishing deeper or larger networks to extract more significant…

This paper proposes a novel Attention-based Multi-Reference Super-resolution network (AMRSR) that, given a low-resolution image, learns to adaptively transfer the most similar texture from multiple reference images to the super-resolution…

In recent years, the attention mechanism contributes significantly to hypergraph based neural networks. However, these methods update the attention weights with the network propagating. That is to say, this type of attention mechanism is…

Most of current display devices are with eight or higher bit-depth. However, the quality of most multimedia tools cannot achieve this bit-depth standard for the generating images. De-quantization can improve the visual quality of low…