LKStar-Yolov8n: an autonomous driving object detection algorithm based on large convolution kernel star structure of Yolov8n
0
Citation
39
Reference
10
Related Paper
Keywords:
Kernel (algebra)
Star (game theory)
Convolution (computer science)
Although video action recognition has achieved great progress in recent years, it is still a challenging task due to the huge computational complexity. Designing a lightweight network is a feasible solution, but it may reduce the spatio-temporal information modeling capability. In this paper, we propose a novel novel spatio-temporal collaborative convolution (denote as "STC-Conv"), which can efficiently encode spatio-temporal information. STC-Conv collaboratively learn spatial and temporal feature in one convolution filter kernel. In short, temporal convolution and spatial convolution are integrated in the one STC convolution kernel, which can effectively reduce the model complexity and improve the computational efficiency. STC-Conv is a universal convolution, which can be applied to the existing 2D CNNs, such as ResNet, DenseNet. The experimental results on the temporal-related dataset Something Something V1 prove the superiority of our method. Noticeably, STC-Conv enjoys more excellent performance than 3D CNNs at even lower computation cost than standard 2D CNNs.
Convolution (computer science)
Kernel (algebra)
ENCODE
Action Recognition
Feature (linguistics)
Cite
Citations (3)
No abstract available.
Cite
Citations (2)
We present a novel deep learning architecture in which the convolution operation leverages heterogeneous kernels. The proposed HetConv (Heterogeneous Kernel-Based Convolution) reduces the computation (FLOPs) and the number of parameters as compared to standard convolution operation while still maintaining representational efficiency. To show the effectiveness of our proposed convolution, we present extensive experimental results on the standard convolutional neural network (CNN) architectures such as VGG and ResNet. We find that after replacing the standard convolutional filters in these architectures with our proposed HetConv filters, we achieve 3X to 8X FLOPs based improvement in speed while still maintaining (and sometimes improving) the accuracy. We also compare our proposed convolutions with group/depth wise convolutions and show that it achieves more FLOPs reduction with significantly higher accuracy.
FLOPS
Kernel (algebra)
Convolution (computer science)
Residual neural network
Cite
Citations (117)
article Free Access Share on Remarks on Algorithm 332: Jacobi polynomials: Algorithm 344: student's t-distribution: Algorithm 351: modified Romberg quadrature: Algorithm 359: factoral analysis of variance Author: Arthur H. J. Sale Univ. of Sydney, Sydney, Australia Univ. of Sydney, Sydney, AustraliaView Profile Authors Info & Claims Communications of the ACMVolume 13Issue 7July 1970 https://doi.org/10.1145/362686.362700Published:01 July 1970Publication History 0citation275DownloadsMetricsTotal Citations0Total Downloads275Last 12 Months10Last 6 weeks3 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my Alerts New Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF
Quadrature (astronomy)
Cite
Citations (0)
Depthwise convolution has gradually become an indispensable operation for modern efficient neural networks and larger kernel sizes ($\ge5$) have been applied to it recently. In this paper, we propose a novel extremely separated convolutional block (XSepConv), which fuses spatially separable convolutions into depthwise convolution to further reduce both the computational cost and parameter size of large kernels. Furthermore, an extra $2\times2$ depthwise convolution coupled with improved symmetric padding strategy is employed to compensate for the side effect brought by spatially separable convolutions. XSepConv is designed to be an efficient alternative to vanilla depthwise convolution with large kernel sizes. To verify this, we use XSepConv for the state-of-the-art architecture MobileNetV3-Small and carry out extensive experiments on four highly competitive benchmark datasets (CIFAR-10, CIFAR-100, SVHN and Tiny-ImageNet) to demonstrate that XSepConv can indeed strike a better trade-off between accuracy and efficiency.
Convolution (computer science)
Kernel (algebra)
Benchmark (surveying)
Cite
Citations (10)
It has long been recognized that the standard convolution is not rotation equivariant and thus not appropriate for downside fisheye images which are rotationally symmetric. This paper introduces Rotational Convolution, a novel convolution that rotates the convolution kernel by characteristics of downside fisheye images. With the four rotation states of the convolution kernel, Rotational Convolution can be implemented on discrete signals. Rotational Convolution improves the performance of different networks in semantic segmentation and object detection markedly, harming the inference speed slightly. Finally, we demonstrate our methods' numerical accuracy, computational efficiency, and effectiveness on the public segmentation dataset THEODORE and our self-built detection dataset SEU-fisheye. Our code is available at: https://github.com/wx19941204/Rotational-Convolution-for-downside-fisheye-images.
Convolution (computer science)
Kernel (algebra)
Convolution theorem
Overlap–add method
Convolution power
Rotational invariance
Cite
Citations (1)
Most of the dynamic convolution algorithms adopted at this stage use the SE attention mechanism, but the attention mechanism, as a key part of dynamic convolution, has not attracted enough attention, and the relevant research is insufficient. In this paper, an exquisite ODConv which is called Channel-Spatial dynamic convolution is proposed. CSConv introduces the spatial attention module and the channel attention module into the ODConv in parallel, so that the convolution kernel pays more attention to the basic characteristics of the input and effectively improves the accuracy of the model and the efficiency of the convolution kernel. The experimental results show that CSConv achieves good results in the four datasets of ImageNet, COCO, HRRSD and DIOR.
Convolution (computer science)
Kernel (algebra)
Overlap–add method
Circular convolution
Cite
Citations (6)
Recently, deep convolution neural networks have been widely used in image classification tasks. In this work, to model the channel correlations in the dense convolutional connections explicitly, an architecture named as DenseNext which integrates modified PSA modules and DenseNet is proposed. By replacing the 3×3 convolution in the DenseNet block with a PSA module, the Dense PSA (D-PSA) block is obtained. To improve the computing efficiency, the modified Dense Asymmetric PSA (DA-PSA) block can be obtained by splitting the big convolution kernel in the D-PSA block into asymmetric convolutions. DenseNeXt can be effectively built by selectively stacking the two convolution modules. Without bells and whistles, the accuracy of DenseNeXt50 on Cifar-10 is 0.52% higher than DenseNet50 and converges faster. DenseNeXts obtain significant improvements and can easily be competent for other vision tasks by fine-tuning.
Convolution (computer science)
Kernel (algebra)
Contextual image classification
Cite
Citations (1)
article Free AccessRemarks on algorithms 372: Algorithm 401: An algorithm to produce complex primes, csieve: an improved algorithm to produce complex primes Author: Paul Bratley Univ. de Montréal, Quebec, Canada Univ. de Montréal, Quebec, CanadaView Profile Authors Info & Claims Communications of the ACMVolume 13Issue 1101 November 1970https://doi.org/10.1145/362790.362805Published:01 November 1970Publication History 0citation192DownloadsMetricsTotal Citations0Total Downloads192Last 12 Months9Last 6 weeks0 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF
Cite
Citations (0)