English
Related papers

Related papers: Scaling Graph Convolutions for Mobile Vision

200 papers

Traditionally, convolutional neural networks (CNN) and vision transformers (ViT) have dominated computer vision. However, recently proposed vision graph neural networks (ViG) provide a new avenue for exploration. Unfortunately, for mobile…

Computer Vision and Pattern Recognition · Computer Science 2023-07-04 Mustafa Munir , William Avery , Radu Marculescu

Vision graph neural networks (ViG) have demonstrated promise in vision tasks as a competitive alternative to conventional convolutional neural nets (CNN) and transformers (ViTs); however, common graph construction methods, such as k-nearest…

Computer Vision and Pattern Recognition · Computer Science 2025-10-16 Mustafa Munir , Alex Zhang , Radu Marculescu

Convolution-based and Transformer-based vision backbone networks process images into the grid or sequence structures, respectively, which are inflexible for capturing irregular objects. Though Vision GNN (ViG) adopts graph-level features…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 Jiafu Wu , Jian Li , Jiangning Zhang , Boshen Zhang , Mingmin Chi , Yabiao Wang , Chengjie Wang

Vision Graph Neural Networks (ViGs) have demonstrated promising performance in image recognition tasks against Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). An essential part of the ViG framework is the node-neighbor…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Hakan Emre Gedik , Andrew Martin , Mustafa Munir , Oguzhan Baser , Radu Marculescu , Sandeep P. Chinchali , Alan C. Bovik

Vision Graph Neural Networks (ViGs) offer a new direction for advancements in vision architectures. While powerful, ViGs often face substantial computational challenges stemming from their graph construction phase, which can hinder their…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Mustafa Munir , Md Mostafijur Rahman , Radu Marculescu

Light-weight convolutional neural networks (CNNs) are the de-facto for mobile vision tasks. Their spatial inductive biases allow them to learn representations with fewer parameters across different vision tasks. However, these networks are…

Computer Vision and Pattern Recognition · Computer Science 2022-03-07 Sachin Mehta , Mohammad Rastegari

Convolutional Neural Networks (CNN) and Vision Transformers (ViT) have dominated the field of Computer Vision (CV). Graph Neural Networks (GNN) have performed remarkably well across diverse domains because they can represent complex…

Computer Vision and Pattern Recognition · Computer Science 2025-04-23 Dhruv Parikh , Jacob Fein-Ashley , Tian Ye , Rajgopal Kannan , Viktor Prasanna

Recently, Vision Graph Neural Network (ViG) has gained considerable attention in computer vision. Despite its groundbreaking innovation, Vision Graph Neural Network encounters key issues including the quadratic computational complexity…

Computer Vision and Pattern Recognition · Computer Science 2025-03-20 Caoshuo Li , Tanzhe Li , Xiaobin Hu , Donghao Luo , Taisong Jin

An increasing need of running Convolutional Neural Network (CNN) models on mobile devices with limited computing power and memory resource encourages studies on efficient model design. A number of efficient architectures have been proposed…

Computer Vision and Pattern Recognition · Computer Science 2019-01-21 Robert J. Wang , Xiang Li , Charles X. Ling

Vision graph neural networks (ViG) offer a new avenue for exploration in computer vision. A major bottleneck in ViGs is the inefficient k-nearest neighbor (KNN) operation used for graph construction. To solve this issue, we propose a new…

Computer Vision and Pattern Recognition · Computer Science 2024-05-14 Mustafa Munir , William Avery , Md Mostafijur Rahman , Radu Marculescu

Recently, Transformer networks have achieved impressive results on a variety of vision tasks. However, most of them are computationally expensive and not suitable for real-world mobile applications. In this work, we present Mobile…

Computer Vision and Pattern Recognition · Computer Science 2022-05-27 Hailong Ma , Xin Xia , Xing Wang , Xuefeng Xiao , Jiashi Li , Min Zheng

Vision Transformer (ViT) has prevailed in computer vision tasks due to its strong long-range dependency modelling ability. \textcolor{blue}{However, its large model size and weak local feature modeling ability hinder its application in real…

Computer Vision and Pattern Recognition · Computer Science 2025-09-12 Yi Zhang , Lingxiao Wei , Bowei Zhang , Ziwei Liu , Kai Yi , Shu Hu

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

MobileViT (MobileViTv1) combines convolutional neural networks (CNNs) and vision transformers (ViTs) to create light-weight models for mobile vision tasks. Though the main MobileViTv1-block helps to achieve competitive state-of-the-art…

Computer Vision and Pattern Recognition · Computer Science 2022-10-07 Shakti N. Wadekar , Abhishek Chaurasia

We propose a novel architecture called the Multi-view Self-Constructing Graph Convolutional Networks (MSCG-Net) for semantic segmentation. Building on the recently proposed Self-Constructing Graph (SCG) module, which makes use of learnable…

Computer Vision and Pattern Recognition · Computer Science 2020-05-19 Qinghui Liu , Michael Kampffmeyer , Robert Jenssen , Arnt-Børre Salberg

Vision transformers (ViTs) have dominated computer vision in recent years. However, ViTs are computationally expensive and not well suited for mobile devices; this led to the prevalence of convolutional neural network (CNN) and ViT-based…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Mustafa Munir , Md Mostafijur Rahman , Radu Marculescu

Vision Graph Neural Networks (ViGs) represent an image as a graph of patch tokens, enabling adaptive, feature-driven neighborhoods. Unlike CNNs with fixed grid biases or Vision Transformers with global token interactions, ViGs rely on…

Computer Vision and Pattern Recognition · Computer Science 2026-04-24 Anvitha Ramachandran , Dhruv Parikh , Viktor Prasanna

While models derived from Vision Transformers (ViTs) have been phonemically surging, pre-trained models cannot seamlessly adapt to arbitrary resolution images without altering the architecture and configuration, such as sampling the…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Song Zhang , Qingzhong Wang , Jiang Bian , Haoyi Xiong

The evolution of MobileNets has laid a solid foundation for neural network applications on mobile end. With the latest MobileNetV3, neural architecture search again claimed its supremacy in network design. Unfortunately, till today all…

Machine Learning · Computer Science 2020-03-04 Xiangxiang Chu , Bo Zhang , Ruijun Xu

In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes. We also describe…

Computer Vision and Pattern Recognition · Computer Science 2019-03-25 Mark Sandler , Andrew Howard , Menglong Zhu , Andrey Zhmoginov , Liang-Chieh Chen
‹ Prev 1 2 3 10 Next ›