English
Related papers

Related papers: RecConv: Efficient Recursive Convolutions for Mult…

200 papers

We propose Re-parameterized Refocusing Convolution (RefConv) as a replacement for regular convolutional layers, which is a plug-and-play module to improve the performance without any inference costs. Specifically, given a pre-trained model,…

Computer Vision and Pattern Recognition · Computer Science 2023-10-17 Zhicheng Cai , Xiaohan Ding , Qiu Shen , Xun Cao

Inspired by the long-range modeling ability of ViTs, large-kernel convolutions are widely studied and adopted recently to enlarge the receptive field and improve model performance, like the remarkable work ConvNeXt which employs 7x7…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Weihao Yu , Pan Zhou , Shuicheng Yan , Xinchao Wang

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…

Computer Vision and Pattern Recognition · Computer Science 2019-03-26 Pravendra Singh , Vinay Kumar Verma , Piyush Rai , Vinay P. Namboodiri

Convolutional neural networks (ConvNets) with large effective receptive field (ERF), still in their early stages, have demonstrated promising effectiveness while constrained by high parameters and FLOPs costs and disrupted asymptotically…

Computer Vision and Pattern Recognition · Computer Science 2025-08-13 Yuhao Wang , Wei Xi

In recent years, there have been attempts to increase the kernel size of Convolutional Neural Nets (CNNs) to mimic the global receptive field of Vision Transformers' (ViTs) self-attention blocks. That approach, however, quickly hit an upper…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Shahaf E. Finder , Roy Amoyal , Eran Treister , Oren Freifeld

Large kernel convolutions offer a scalable alternative to vision transformers for high-resolution 3D volumetric analysis, yet naively increasing kernel size often leads to optimization instability. Motivated by the spatial bias inherent in…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Ho Hin Lee , Quan Liu , Shunxing Bao , Yuankai Huo , Bennett A. Landman

When designing Convolutional Neural Networks (CNNs), one must select the size\break of the convolutional kernels before training. Recent works show CNNs benefit from different kernel sizes at different layers, but exploring all possible…

Computer Vision and Pattern Recognition · Computer Science 2022-03-18 David W. Romero , Robert-Jan Bruintjes , Jakub M. Tomczak , Erik J. Bekkers , Mark Hoogendoorn , Jan C. van Gemert

View synthesis methods using implicit continuous shape representations learned from a set of images, such as the Neural Radiance Field (NeRF) method, have gained increasing attention due to their high quality imagery and scalability to high…

Computer Vision and Pattern Recognition · Computer Science 2021-05-20 Guo-Wei Yang , Wen-Yang Zhou , Hao-Yang Peng , Dun Liang , Tai-Jiang Mu , Shi-Min Hu

Continuous convolution has recently gained prominence due to its ability to handle irregularly sampled data and model long-term dependency. Also, the promising experimental results of using large convolutional kernels have catalyzed the…

Computer Vision and Pattern Recognition · Computer Science 2023-04-06 Sanghyeon Kim , Eunbyung Park

We revisit large kernel design in modern convolutional neural networks (CNNs). Inspired by recent advances in vision transformers (ViTs), in this paper, we demonstrate that using a few large convolutional kernels instead of a stack of small…

Computer Vision and Pattern Recognition · Computer Science 2022-04-05 Xiaohan Ding , Xiangyu Zhang , Yizhuang Zhou , Jungong Han , Guiguang Ding , Jian Sun

Look-up table(LUT)-based methods have shown the great efficacy in single image super-resolution (SR) task. However, previous methods ignore the essential reason of restricted receptive field (RF) size in LUT, which is caused by the…

Image and Video Processing · Electrical Eng. & Systems 2023-07-18 Guandu Liu , Yukang Ding , Mading Li , Ming Sun , Xing Wen , Bin Wang

As convolution has empowered many smart applications, dynamic convolution further equips it with the ability to adapt to diverse inputs. However, the static and dynamic convolutions are either layout-agnostic or computation-heavy, making it…

Computer Vision and Pattern Recognition · Computer Science 2022-03-23 Jierun Chen , Tianlang He , Weipeng Zhuo , Li Ma , Sangtae Ha , S. -H. Gary Chan

In the realm of resource-constrained mobile vision tasks, the pursuit of efficiency and performance consistently drives innovation in lightweight Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). While ViTs excel at…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Mingshu Zhao , Yi Luo , Yong Ouyang

In convolutional neural networks, the convolutions are conventionally performed using a square kernel with a fixed N $\times$ N receptive field (RF). However, what matters most to the network is the effective receptive field (ERF) that…

Computer Vision and Pattern Recognition · Computer Science 2023-04-21 Qi Chen , Chao Li , Jia Ning , Stephen Lin , Kun He

Convolutional architectures have emerged as powerful alternatives to Transformers for sequence modeling. The primary advantage is that they offer improved theoretical sequence length complexity by leveraging the Fast Fourier Transform…

Machine Learning · Computer Science 2026-05-12 Linda Friso , Annie Marsden , Xinyi Chen , Arushi Gupta , Peter Bartlett , Mark Braverman , Elad Hazan

Convolutional neural networks have witnessed remarkable improvements in computational efficiency in recent years. A key driving force has been the idea of trading-off model expressivity and efficiency through a combination of $1\times 1$…

Computer Vision and Pattern Recognition · Computer Science 2020-04-08 Zhichao Lu , Kalyanmoy Deb , Vishnu Naresh Boddeti

Convolutional layers are one of the basic building blocks of modern deep neural networks. One fundamental assumption is that convolutional kernels should be shared for all examples in a dataset. We propose conditionally parameterized…

Computer Vision and Pattern Recognition · Computer Science 2020-09-07 Brandon Yang , Gabriel Bender , Quoc V. Le , Jiquan Ngiam

Light-weight convolutional neural networks (CNNs) suffer performance degradation as their low computational budgets constrain both the depth (number of convolution layers) and the width (number of channels) of CNNs, resulting in limited…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Yinpeng Chen , Xiyang Dai , Mengchen Liu , Dongdong Chen , Lu Yuan , Zicheng Liu

In this work, we tackle model efficiency by exploiting redundancy in the \textit{implicit structure} of the building blocks of convolutional neural networks. We start our analysis by introducing a general definition of Composite Kernel…

Computer Vision and Pattern Recognition · Computer Science 2020-11-03 Yash Bhalgat , Yizhe Zhang , Jamie Lin , Fatih Porikli

Neural Representations for Videos (NeRV) encode entire video sequences within neural network parameters, offering an alternative paradigm to conventional video codecs. However, the convolutional decoder of NeRV remains computationally…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Tamer Shanableh
‹ Prev 1 2 3 10 Next ›