Related papers: Gradient-Guided Learning Network for Infrared Smal…
Binary semantic segmentation in computer vision is a fundamental problem. As a model-based segmentation method, the graph-cut approach was one of the most successful binary segmentation methods thanks to its global optimality guarantee of…
Thermal infrared (TIR) images typically lack detailed features and have low contrast, making it challenging for conventional feature extraction models to capture discriminative target characteristics. As a result, trackers are often…
Recently, a series of works in computer vision have shown promising results on various image and video understanding tasks using self-attention. However, due to the quadratic computational and memory complexities of self-attention, these…
While 3D Gaussian Splatting enables high-quality real-time rendering, existing Gaussian-based frameworks for 3D semantic segmentation still face significant challenges in boundary recognition accuracy. To address this, we propose a novel…
Infrared and visible image fusion aims to integrate complementary information from co-registered source images to produce a single, informative result. Most learning-based approaches train with a combination of structural similarity loss,…
For Convolutional Neural Network-based object detection, there is a typical dilemma: the spatial information is well kept in the shallow layers which unfortunately do not have enough semantic information, while the deep layers have a high…
In recent years, the challenge of 3D shape analysis within point cloud data has gathered significant attention in computer vision. Addressing the complexities of effective 3D information representation and meaningful feature extraction for…
This paper investigates the problem of recovering hyperspectral (HS) images from single RGB images. To tackle such a severely ill-posed problem, we propose a physically-interpretable, compact, efficient, and end-to-end learning-based…
Despite the powerful feature extraction capability of Convolutional Neural Networks, there are still some challenges in saliency detection. In this paper, we focus on two aspects of challenges: i) Since salient objects appear in various…
Depth information matters in RGB-D semantic segmentation task for providing additional geometric information to color images. Most existing methods exploit a multi-stage fusion strategy to propagate depth feature to the RGB branch. However,…
Image segmentation is a fundamental task in computer vision. Data annotation for training supervised methods can be labor-intensive, motivating unsupervised methods. Current approaches often rely on extracting deep features from pre-trained…
The mining and utilization of features directly affect the classification performance of models used in the classification and recognition of hyperspectral remote sensing images. Traditional models usually conduct feature mining from a…
Graph Neural Network (GNN) is an emerging technique for graph-based learning tasks such as node classification. In this work, we reveal the vulnerability of GNN to the imbalance of node labels. Traditional solutions for imbalanced…
In recent years, deep convolutional neural network-based segmentation methods have achieved state-of-the-art performance for many medical analysis tasks. However, most of these approaches rely on optimizing the U-Net structure or adding new…
The great success neural networks have achieved is inseparable from the application of gradient-descent (GD) algorithms. Based on GD, many variant algorithms have emerged to improve the GD optimization process. The gradient for…
Recently, graph-based and Transformer-based deep learning networks have demonstrated excellent performances on various point cloud tasks. Most of the existing graph methods are based on static graph, which take a fixed input to establish…
This study explores the potential of graph neural networks (GNNs) to enhance semantic segmentation across diverse image modalities. We evaluate the effectiveness of a novel GNN-based U-Net architecture on three distinct datasets: PascalVOC,…
Existing graph-network-based few-shot learning methods obtain similarity between nodes through a convolution neural network (CNN). However, the CNN is designed for image data with spatial information rather than vector form node feature. In…
Restoring images from low-light data is a challenging problem. Most existing deep-network based algorithms are designed to be trained with pairwise images. Due to the lack of real-world datasets, they usually perform poorly when generalized…
In this work, we introduce Gradient Siamese Network (GSN) for image quality assessment. The proposed method is skilled in capturing the gradient features between distorted images and reference images in full-reference image quality…