Related papers: ParC-Net: Position Aware Circular Convolution with…
What is an image and how to extract latent features? Convolutional Networks (ConvNets) consider an image as organized pixels in a rectangular shape and extract features via convolutional operation in local region; Vision Transformers (ViTs)…
To improve the discriminative and generalization ability of lightweight network for face recognition, we propose an efficient variable group convolutional network called VarGFaceNet. Variable group convolution is introduced by VarGNet to…
We introduce PointConvFormer, a novel building block for point cloud based deep network architectures. Inspired by generalization theory, PointConvFormer combines ideas from point convolution, where filter weights are only based on relative…
Convolutional Neural networks (CNN) have been the first choice of paradigm in many computer vision applications. The convolution operation however has a significant weakness which is it only operates on a local neighborhood of pixels, thus…
Convolutional networks are at the core of most state-of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to become mainstream, yielding substantial gains in various…
This paper analyzes the design choices of face detection architecture that improve efficiency of computation cost and accuracy. Specifically, we re-examine the effectiveness of the standard convolutional block as a lightweight backbone…
In many computer vision tasks, we expect a particular behavior of the output with respect to rotations of the input image. If this relationship is explicitly encoded, instead of treated as any other variation, the complexity of the problem…
The superior performance of Deformable Convolutional Networks arises from its ability to adapt to the geometric variations of objects. Through an examination of its adaptive behavior, we observe that while the spatial support for its neural…
We propose a new convolution called Dynamic Region-Aware Convolution (DRConv), which can automatically assign multiple filters to corresponding spatial regions where features have similar representation. In this way, DRConv outperforms…
Vision transformer (ViT) has achieved competitive accuracy on a variety of computer vision applications, but its computational cost impedes the deployment on resource-limited mobile devices. We explore the sparsity in ViT and observe that…
While transformer architectures have dominated computer vision in recent years, these models cannot easily be deployed on hardware with limited resources for autonomous driving tasks that require real-time-performance. Their computational…
Modern vision transformers leverage visually inspired local interaction between pixels through attention computed within window or grid regions, in contrast to the global attention employed in the original ViT. Regional attention restricts…
We present an efficient high-resolution network, Lite-HRNet, for human pose estimation. We start by simply applying the efficient shuffle block in ShuffleNet to HRNet (high-resolution network), yielding stronger performance over popular…
In recent developments in the field of Computer Vision, a rise is seen in the use of transformer-based architectures. They are surpassing the state-of-the-art set by CNN architectures in accuracy but on the other hand, they are…
Transformer with self-attention has led to the revolutionizing of natural language processing field, and recently inspires the emergence of Transformer-style architecture design with competitive results in numerous computer vision tasks.…
Long-range contextual information is essential for achieving high-performance semantic segmentation. Previous feature re-weighting methods demonstrate that using global context for re-weighting feature channels can effectively improve the…
Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically study model scaling and identify that…
Deep convolutional neural networks have achieved remarkable success in computer vision. However, deep neural networks require large computing resources to achieve high performance. Although depthwise separable convolution can be an…
Point cloud-based large scale place recognition is fundamental for many applications like Simultaneous Localization and Mapping (SLAM). Although many models have been proposed and have achieved good performance by learning short-range local…
In many real-time applications, the deployment of deep neural networks is constrained by high computational cost and efficient lightweight neural networks are widely concerned. In this paper, we propose that depthwise convolution (DWC) is…