Related papers: Optimized Vectorizing of Building Structures with …
Recently, transformer and multi-layer perceptron (MLP) architectures have achieved impressive results on various vision tasks. A few works investigated manually combining those operators to design visual network architectures, and can…
Vision Transformers have achieved great success in computer visions, delivering exceptional performance across various tasks. However, their inherent reliance on sequential input enforces the manual partitioning of images into patch…
Neural networks rely on convolutions to aggregate spatial information. However, spatial convolutions are expensive in terms of model size and computation, both of which grow quadratically with respect to kernel size. In this paper, we…
Vision transformers have become popular as a possible substitute to convolutional neural networks (CNNs) for a variety of computer vision applications. These transformers, with their ability to focus on global relationships in images, offer…
This paper proposes a novel heterogeneous grid convolution that builds a graph-based image representation by exploiting heterogeneity in the image content, enabling adaptive, efficient, and controllable computations in a convolutional…
Very recently, Window-based Transformers, which computed self-attention within non-overlapping local windows, demonstrated promising results on image classification, semantic segmentation, and object detection. However, less study has been…
Graph neural networks (GNNs) have become a workhorse approach for learning from data defined over irregular domains, typically by implicitly assuming that the data structure is represented by a homophilic graph. However, recent works have…
Building footprint information is an essential ingredient for 3-D reconstruction of urban models. The automatic generation of building footprints from satellite images presents a considerable challenge due to the complexity of building…
Convolutional neural network (CNN) delivers impressive achievements in computer vision and machine learning field. However, CNN incurs high computational complexity, especially for vision quality applications because of large image…
Convolutional Neural Networks have revolutionized vision applications. There are image domains and representations, however, that cannot be handled by standard CNNs (e.g., spherical images, superpixels). Such data are usually processed…
Inspired by the recent success of methods that employ shape priors to achieve robust 3D reconstructions, we propose a novel recurrent neural network architecture that we call the 3D Recurrent Reconstruction Neural Network (3D-R2N2). The…
Graph neural networks (GNN) has been demonstrated to be effective in classifying graph structures. To further improve the graph representation learning ability, hierarchical GNN has been explored. It leverages the differentiable pooling to…
Convolutional neural networks have achieved great success in various vision tasks; however, they incur heavy resource costs. By using deeper and wider networks, network accuracy can be improved rapidly. However, in an environment with…
The single image super-resolution(SISR) algorithms under deep learning currently have two main models, one based on convolutional neural networks and the other based on Transformer. The former uses the stacking of convolutional layers with…
In the past few years, convolutional neural networks (CNNs), particularly U-Net, have been the prevailing technique in the medical image processing era. Specifically, the seminal U-Net, as well as its alternatives, have successfully managed…
Recently, transformer and multi-layer perceptron (MLP) architectures have achieved impressive results on various vision tasks. However, how to effectively combine those operators to form high-performance hybrid visual architectures still…
The shift from Convolutional Neural Networks to Transformers has reshaped computer vision, yet these two architectural families are typically viewed as fundamentally distinct. We argue that convolution and self-attention, despite their…
Current state-of-the-art visual recognition systems usually rely on the following pipeline: (a) pretraining a neural network on a large-scale dataset (e.g., ImageNet) and (b) finetuning the network weights on a smaller, task-specific…
Graph neural networks (GNNs) model representations from networked data and allow for decentralized inference through localized communications. Existing GNN architectures often assume ideal communications and ignore potential channel…
By recursively summing node features over entire neighborhoods, spatial graph convolution operators have been heralded as key to the success of Graph Neural Networks (GNNs). Yet, despite the multiplication of GNN methods across tasks and…