English
Related papers

Related papers: Dynamic Region-Aware Convolution

200 papers

We introduce Region-Aware Deformable Convolution (RAD-Conv), a new convolutional operator that enhances neural networks' ability to adapt to complex image structures. Unlike traditional deformable convolutions, which are limited to fixed…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Abolfazl Saheban Maleki , Maryam Imani

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

We tackle the problem of using 3D information in convolutional neural networks for down-stream recognition tasks. Using depth as an additional channel alongside the RGB input has the scale variance problem present in image convolution based…

Computer Vision and Pattern Recognition · Computer Science 2018-12-05 Hang Chu , Wei-Chiu Ma , Kaustav Kundu , Raquel Urtasun , Sanja Fidler

Real-SR endeavors to produce high-resolution images with rich details while mitigating the impact of multiple degradation factors. Although existing methods have achieved impressive achievements in detail recovery, they still fall short…

Image and Video Processing · Electrical Eng. & Systems 2024-05-14 Long Peng , Yang Cao , Renjing Pei , Wenbo Li , Jiaming Guo , Xueyang Fu , Yang Wang , Zheng-Jun Zha

While Dynamic Convolution (DY-Conv) has shown promising performance by enabling adaptive weight selection through multiple parallel weights combined with an attention mechanism, the frequency response of these weights tends to exhibit high…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Linwei Chen , Lin Gu , Liang Li , Chenggang Yan , Ying Fu

Convolution is one of the basic building blocks of CNN architectures. Despite its common use, standard convolution has two main shortcomings: Content-agnostic and Computation-heavy. Dynamic filters are content-adaptive, while further…

Computer Vision and Pattern Recognition · Computer Science 2021-04-30 Jingkai Zhou , Varun Jampani , Zhixiong Pi , Qiong Liu , Ming-Hsuan Yang

Dynamic convolution achieves better performance for efficient CNNs at the cost of negligible FLOPs increase. However, the performance increase can not match the significantly expanded number of parameters, which is the main bottleneck in…

Computer Vision and Pattern Recognition · Computer Science 2023-05-29 Shwai He , Chenbo Jiang , Daize Dong , Liang Ding

The convolution operation is a powerful tool for feature extraction and plays a prominent role in the field of computer vision. However, when targeting the pixel-wise tasks like image fusion, it would not fully perceive the particularity of…

Computer Vision and Pattern Recognition · Computer Science 2021-07-27 Zi-Rong Jin , Liang-Jian Deng , Tai-Xiang Jiang , Tian-Jing Zhang

Aiming to obtain a high-resolution image, pansharpening involves the fusion of a multi-spectral image (MS) and a panchromatic image (PAN), the low-level vision task remaining significant and challenging in contemporary research. Most…

Computer Vision and Pattern Recognition · Computer Science 2025-08-18 Xuanyu Liu , Bonan An

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 image denoising networks, feature scaling is widely used to enlarge the receptive field size and reduce computational costs. This practice, however, also leads to the loss of high-frequency information and fails to consider within-scale…

Computer Vision and Pattern Recognition · Computer Science 2023-04-04 Hao Shen , Zhong-Qiu Zhao , Wandi Zhang

Convolutional layers are the core building blocks of Convolutional Neural Networks (CNNs). In this paper, we propose to augment a convolutional layer with an additional depthwise convolution, where each input channel is convolved with a…

Computer Vision and Pattern Recognition · Computer Science 2020-06-23 Jinming Cao , Yangyan Li , Mingchao Sun , Ying Chen , Dani Lischinski , Daniel Cohen-Or , Baoquan Chen , Changhe Tu

Despite the remarkable success of deep learning, an optimal convolution operation on point clouds remains elusive owing to their irregular data structure. Existing methods mainly focus on designing an effective continuous kernel function…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Sungmin Woo , Dogyoon Lee , Sangwon Hwang , Woojin Kim , Sangyoun Lee

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

A key challenge for RGB-D segmentation is how to effectively incorporate 3D geometric information from the depth channel into 2D appearance features. We propose to model the effective receptive field of 2D convolution based on the scale and…

Computer Vision and Pattern Recognition · Computer Science 2019-10-04 Yunlu Chen , Thomas Mensink , Efstratios Gavves

Learning a single static convolutional kernel in each convolutional layer is the common training paradigm of modern Convolutional Neural Networks (CNNs). Instead, recent research in dynamic convolution shows that learning a linear…

Computer Vision and Pattern Recognition · Computer Science 2022-09-19 Chao Li , Aojun Zhou , Anbang Yao

This work introduces pyramidal convolution (PyConv), which is capable of processing the input at multiple filter scales. PyConv contains a pyramid of kernels, where each level involves different types of filters with varying size and depth,…

Computer Vision and Pattern Recognition · Computer Science 2020-06-23 Ionut Cosmin Duta , Li Liu , Fan Zhu , Ling Shao

Object detection has made substantial progress in the last decade, due to the capability of convolution in extracting local context of objects. However, the scales of objects are diverse and current convolution can only process single-scale…

Computer Vision and Pattern Recognition · Computer Science 2022-06-17 Junliang Chen , Xiaodong Zhao , Linlin Shen

Despite their strong modeling capacities, Convolutional Neural Networks (CNNs) are often scale-sensitive. For enhancing the robustness of CNNs to scale variance, multi-scale feature fusion from different layers or filters attracts great…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 Duo Li , Anbang Yao , Qifeng Chen
‹ Prev 1 2 3 10 Next ›