Related papers: LABNet: Local Graph Aggregation Network with Class…

Most works on person re-identification (ReID) take advantage of large backbone networks such as ResNet, which are designed for image classification instead of ReID, for feature extraction. However, these backbones may not be computationally…

Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and thus cannot preserve important information. As another…

Clustering (or community detection) on multilayer graphs poses several additional complications with respect to standard graphs as different layers may be characterized by different structures and types of information. One of the major…

Global average pooling (GAP) allows to localize discriminative information for recognition [40]. While GAP helps the convolution neural network to attend to the most discriminative features of an object, it may suffer if that information is…

Sparse local feature extraction is usually believed to be of important significance in typical vision tasks such as simultaneous localization and mapping, image matching and 3D reconstruction. At present, it still has some deficiencies…

The rapid development of generative AI has made AI-generated images increasingly realistic and high-resolution. Most AI-generated image detection architectures typically downsample images before inputting them into models, risking the loss…

Traditional grid/neighbor-based static pooling has become a constraint for point cloud geometry analysis. In this paper, we propose DAR-Net, a novel network architecture that focuses on dynamic feature aggregation. The central idea of…

Graph neural networks (GNNs) have revolutionized the field of machine learning on non-Euclidean data such as graphs and networks. GNNs effectively implement node representation learning through neighborhood aggregation and achieve…

Few-shot learning focuses on learning a new visual concept with very limited labelled examples. A successful approach to tackle this problem is to compare the similarity between examples in a learned metric space based on convolutional…

Scene parsing from images is a fundamental yet challenging problem in visual content understanding. In this dense prediction task, the parsing model assigns every pixel to a categorical label, which requires the contextual information of…

We present a novel local improvement scheme for the perfectly balanced graph partitioning problem. This scheme encodes local searches that are not restricted to a balance constraint into a model allowing us to find combinations of these…

A critical bottleneck in supervised machine learning is the need for large amounts of labeled data which is expensive and time consuming to obtain. However, it has been shown that a small amount of labeled data, while insufficient to…

This paper aims to improve the Warping Planer Object Detection Network (WPOD-Net) using feature engineering to increase accuracy. What problems are solved using the Warping Object Detection Network using feature engineering? More…

Lane detection is critical for autonomous driving and ad-vanced driver assistance systems (ADAS). While recent methods like CLRNet achieve strong performance, they struggle under adverse con-ditions such as extreme weather, illumination…

Non-local self-similarity is well-known to be an effective prior for the image denoising problem. However, little work has been done to incorporate it in convolutional neural networks, which surpass non-local model-based methods despite…

Graph-level clustering remains a pivotal yet formidable challenge in graph learning. Recently, the integration of deep learning with representation learning has demonstrated notable advancements, yielding performance enhancements to a…

Extracting effective and discriminative features is very important for addressing the challenging person re-identification (re-ID) task. Prevailing deep convolutional neural networks (CNNs) usually use high-level features for identifying…

Image deraining is a fundamental, yet not well-solved problem in computer vision and graphics. The traditional image deraining approaches commonly behave ineffectively in medium and heavy rain removal, while the learning-based ones lead to…

Many real-world problems can be represented as graph-based learning problems. In this paper, we propose a novel framework for learning spatial and attentional convolution neural networks on arbitrary graphs. Different from previous…

Deep learning has gained great success in various classification tasks. Typically, deep learning models learn underlying features directly from data, and no underlying relationship between classes are included. Similarity between classes…