English
Related papers

Related papers: Adaptive Convolutions with Per-pixel Dynamic Filte…

200 papers

Convolutions are the fundamental building block of CNNs. The fact that their weights are spatially shared is one of the main reasons for their widespread use, but it also is a major limitation, as it makes convolutions content agnostic. We…

Computer Vision and Pattern Recognition · Computer Science 2019-04-12 Hang Su , Varun Jampani , Deqing Sun , Orazio Gallo , Erik Learned-Miller , Jan Kautz

Efficient fine-tuning methods are critical to address the high computational and parameter complexity while adapting large pre-trained models to downstream tasks. Our study is inspired by prior research that represents each convolution…

Computer Vision and Pattern Recognition · Computer Science 2025-02-27 Wei Chen , Zichen Miao , Qiang Qiu

In this work, we present the depth-adaptive deep neural network using a depth map for semantic segmentation. Typical deep neural networks receive inputs at the predetermined locations regardless of the distance from the camera. This fixed…

Computer Vision and Pattern Recognition · Computer Science 2018-01-30 Byeongkeun Kang , Yeejin Lee , Truong Q. Nguyen

Convolutional neural networks excel in a number of computer vision tasks. One of their most crucial architectural elements is the effective receptive field size, that has to be manually set to accommodate a specific task. Standard solutions…

Computer Vision and Pattern Recognition · Computer Science 2020-02-07 Domen Tabernik , Matej Kristan , Aleš Leonardis

This paper introduces versatile filters to construct efficient convolutional neural networks that are widely used in various visual recognition tasks. Considering the demands of efficient deep learning techniques running on cost-effective…

Computer Vision and Pattern Recognition · Computer Science 2021-09-23 Kai Han , Yunhe Wang , Chang Xu , Chunjing Xu , Enhua Wu , Dacheng Tao

We propose a simple and generic layer formulation that extends the properties of convolutional layers to any domain that can be described by a graph. Namely, we use the support of its adjacency matrix to design learnable weight sharing…

Machine Learning · Computer Science 2017-10-06 Jean-Charles Vialatte , Vincent Gripon , Gilles Coppin

Convolutional networks are not aware of an object's geometric variations, which leads to inefficient utilization of model and data capacity. To overcome this issue, recent works on deformation modeling seek to spatially reconfigure the data…

Computer Vision and Pattern Recognition · Computer Science 2020-02-13 Hang Gao , Xizhou Zhu , Steve Lin , Jifeng Dai

This paper tackles the problem of motion deblurring of dynamic scenes. Although end-to-end fully convolutional designs have recently advanced the state-of-the-art in non-uniform motion deblurring, their performance-complexity trade-off is…

Computer Vision and Pattern Recognition · Computer Science 2024-02-12 Maitreya Suin , Kuldeep Purohit , A. N. Rajagopalan

This paper tackles the problem of dynamic scene deblurring. Although end-to-end fully convolutional designs have recently advanced the state-of-the-art in non-uniform motion deblurring, their performance-complexity trade-off is still…

Image and Video Processing · Electrical Eng. & Systems 2022-01-04 Maitreya Suin , Kuldeep Purohit , A. N. Rajagopalan

Convolutional neural networks (CNNs) excel in local feature extraction while Transformers are superior in processing global semantic information. By leveraging the strengths of both, hybrid Transformer-CNN networks have become the major…

Computer Vision and Pattern Recognition · Computer Science 2025-01-07 Xu Ma , Mengsheng Chen , Junhui Zhang , Lijuan Song , Fang Du , Zhenhua Yu

State-of-the-art methods for computer vision rely heavily on the translation equivariance and spatial sharing properties of convolutional layers without explicitly taking into consideration the input content. Modern techniques employ deep…

Computer Vision and Pattern Recognition · Computer Science 2019-11-26 Filippos Kokkinos , Ioannis Marras , Matteo Maggioni , Gregory Slabaugh , Stefanos Zafeiriou

Deformable convolutional networks have demonstrated outstanding performance in object recognition tasks with an effective feature extraction. Unlike standard convolution, the deformable convolution decides the receptive field size using…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-06-16 Saehyun Ahn , Jung-Woo Chang , Suk-Ju Kang

The paper introduces the weighted convolution, a novel approach to the convolution for signals defined on regular grids (e.g., 2D images) through the application of an optimal density function to scale the contribution of neighbouring…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Simone Cammarasana , Giuseppe Patanè

In a traditional convolutional layer, the learned filters stay fixed after training. In contrast, we introduce a new framework, the Dynamic Filter Network, where filters are generated dynamically conditioned on an input. We show that this…

Machine Learning · Computer Science 2016-06-07 Bert De Brabandere , Xu Jia , Tinne Tuytelaars , Luc Van Gool

We present data structures and algorithms for native implementations of discrete convolution operators over Adaptive Particle Representations (APR) of images on parallel computer architectures. The APR is a content-adaptive image…

Computer Vision and Pattern Recognition · Computer Science 2022-07-13 Joel Jonsson , Bevan L. Cheeseman , Suryanarayana Maddu , Krzysztof Gonciarz , Ivo F. Sbalzarini

In this paper, we consider domain-invariant deep learning by explicitly modeling domain shifts with only a small amount of domain-specific parameters in a Convolutional Neural Network (CNN). By exploiting the observation that a…

Machine Learning · Computer Science 2020-09-30 Ze Wang , Xiuyuan Cheng , Guillermo Sapiro , Qiang Qiu

We devise a universal adaptive neural layer to "learn" optimal frequency filter for each image together with the weights of the base neural network that performs some computer vision task. The proposed approach takes the source image in the…

Image and Video Processing · Electrical Eng. & Systems 2022-11-15 Viktor Shipitsin , Iaroslav Bespalov , Dmitry V. Dylov

Dynamic convolution enhances model capacity by adaptively combining multiple kernels, yet faces critical trade-offs: prior works either (1) incur significant parameter overhead by scaling kernel numbers linearly, (2) compromise inference…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Haiduo Huang , Yadong Zhang , Yinghui Xu , Pengju Ren

Convolutional networks have achieved great success in various vision tasks. This is mainly due to a considerable amount of research on network structure. In this study, instead of focusing on architectures, we focused on the convolution…

Computer Vision and Pattern Recognition · Computer Science 2019-02-12 Yunho Jeon , Junmo Kim

FPGAs provide a flexible and efficient platform to accelerate rapidly-changing algorithms for computer vision. The majority of existing work focuses on accelerating image classification, while other fundamental vision problems, including…

Image and Video Processing · Electrical Eng. & Systems 2020-03-25 Qijing Huang , Dequan Wang , Yizhao Gao , Yaohui Cai , Zhen Dong , Bichen Wu , Kurt Keutzer , John Wawrzynek
‹ Prev 1 2 3 10 Next ›