English
Related papers

Related papers: Fast Sparse 3D Convolution Network with VDB

200 papers

Deep convolution Neural Network (DCNN) has been widely used in computer vision tasks. However, for edge devices even inference has too large computational complexity and data access amount. The inference latency of state-of-the-art models…

Hardware Architecture · Computer Science 2025-09-09 Kuan-Ting Lin , Ching-Te Chiu , Jheng-Yi Chang , Shi-Zong Huang , Yu-Ting Li

Modern efficient Convolutional Neural Networks(CNNs) always use Depthwise Separable Convolutions(DSCs) and Neural Architecture Search(NAS) to reduce the number of parameters and the computational complexity. But some inherent…

Computer Vision and Pattern Recognition · Computer Science 2022-07-22 Liangqi Zhang , Haibo Shen , Yihao Luo , Xiang Cao , Leixilan Pan , Tianjiang Wang , Qi Feng

3D scenes are dominated by a large number of background points, which is redundant for the detection task that mainly needs to focus on foreground objects. In this paper, we analyze major components of existing sparse 3D CNNs and find that…

Computer Vision and Pattern Recognition · Computer Science 2022-09-29 Jianhui Liu , Yukang Chen , Xiaoqing Ye , Zhuotao Tian , Xiao Tan , Xiaojuan Qi

We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. Our findings are three-fold: 1) 3D ConvNets are…

Computer Vision and Pattern Recognition · Computer Science 2015-10-08 Du Tran , Lubomir Bourdev , Rob Fergus , Lorenzo Torresani , Manohar Paluri

Generally, convolutional neural networks (CNNs) process data on a regular grid, e.g. data generated by ordinary cameras. Designing CNNs for sparse and irregularly spaced input data is still an open research problem with numerous…

Computer Vision and Pattern Recognition · Computer Science 2019-08-06 Abdelrahman Eldesokey , Michael Felsberg , Fahad Shahbaz Khan

We present Point-Voxel CNN (PVCNN) for efficient, fast 3D deep learning. Previous work processes 3D data using either voxel-based or point-based NN models. However, both approaches are computationally inefficient. The computation cost and…

Computer Vision and Pattern Recognition · Computer Science 2019-12-11 Zhijian Liu , Haotian Tang , Yujun Lin , Song Han

Contemporary Deep Neural Network (DNN) contains millions of synaptic connections with tens to hundreds of layers. The large computation and memory requirements pose a challenge to the hardware design. In this work, we leverage the intrinsic…

Machine Learning · Computer Science 2017-11-07 Jingyang Zhu , Jingbo Jiang , Xizi Chen , Chi-Ying Tsui

The predictive power and overall computational efficiency of Diffusion-convolutional neural networks make them an attractive choice for node classification tasks. However, a naive dense-tensor-based implementation of DCNNs leads to…

Machine Learning · Computer Science 2017-10-27 James Atwood , Siddharth Pal , Don Towsley , Ananthram Swami

Sparse methods and the use of Winograd convolutions are two orthogonal approaches, each of which significantly accelerates convolution computations in modern CNNs. Sparse Winograd merges these two and thus has the potential to offer a…

Computer Vision and Pattern Recognition · Computer Science 2017-10-17 Sheng Li , Jongsoo Park , Ping Tak Peter Tang

3D convolution neural networks (CNNs) have been the prevailing option for video recognition. To capture the temporal information, 3D convolutions are computed along the sequences, leading to cubically growing and expensive computations. To…

Computer Vision and Pattern Recognition · Computer Science 2023-03-07 Junyan Wang , Zhenhong Sun , Yichen Qian , Dong Gong , Xiuyu Sun , Ming Lin , Maurice Pagnucco , Yang Song

In recent years, there has been a significant increase in the utilization of deep learning methods, particularly convolutional neural networks (CNNs), which have emerged as the dominant approach in various domains that involve structured…

Machine Learning · Computer Science 2024-04-09 Chester Luo , Kevin Lai

Purpose: The aim of this work is to demonstrate that convolutional neural networks (CNN) can be applied to extremely sparse image libraries by subdivision of the original image datasets. Methods: Image datasets from a conventional digital…

Computer Vision and Pattern Recognition · Computer Science 2020-10-27 Johan P. Boetker

We introduce Deformable Convolution v4 (DCNv4), a highly efficient and effective operator designed for a broad spectrum of vision applications. DCNv4 addresses the limitations of its predecessor, DCNv3, with two key enhancements: 1.…

Computer Vision and Pattern Recognition · Computer Science 2024-01-15 Yuwen Xiong , Zhiqi Li , Yuntao Chen , Feng Wang , Xizhou Zhu , Jiapeng Luo , Wenhai Wang , Tong Lu , Hongsheng Li , Yu Qiao , Lewei Lu , Jie Zhou , Jifeng Dai

3D object detectors usually rely on hand-crafted proxies, e.g., anchors or centers, and translate well-studied 2D frameworks to 3D. Thus, sparse voxel features need to be densified and processed by dense prediction heads, which inevitably…

Computer Vision and Pattern Recognition · Computer Science 2023-03-21 Yukang Chen , Jianhui Liu , Xiangyu Zhang , Xiaojuan Qi , Jiaya Jia

Very deep convolutional neural networks (CNNs) have been firmly established as the primary methods for many computer vision tasks. However, most state-of-the-art CNNs are large, which results in high inference latency. Recently, depth-wise…

Computer Vision and Pattern Recognition · Computer Science 2025-01-07 Yihui He , Jianing Qian , Jianren Wang , Cindy X. Le , Congrui Hetang , Qi Lyu , Wenping Wang , Tianwei Yue

The compression of deep neural networks (DNNs) to reduce inference cost becomes increasingly important to meet realistic deployment requirements of various applications. There have been a significant amount of work regarding network…

Machine Learning · Computer Science 2020-11-12 Tianyi Chen , Bo Ji , Yixin Shi , Tianyu Ding , Biyi Fang , Sheng Yi , Xiao Tu

2D convolution (Conv2d), which is responsible for extracting features from the input image, is one of the key modules of a convolutional neural network (CNN). However, Conv2d is vulnerable to image corruptions and adversarial samples. It is…

Computer Vision and Pattern Recognition · Computer Science 2022-03-21 Lida Li , Shuai Li , Kun Wang , Xiangchu Feng , Lei Zhang

Detection and tracking of moving objects is an essential component in environmental perception for autonomous driving. In the flourishing field of multi-view 3D camera-based detectors, different transformer-based pipelines are designed to…

Computer Vision and Pattern Recognition · Computer Science 2023-07-04 Yining Shi , Jingyan Shen , Yifan Sun , Yunlong Wang , Jiaxin Li , Shiqi Sun , Kun Jiang , Diange Yang

In this paper, we present a robust method for scene recognition, which leverages Convolutional Neural Networks (CNNs) features and Sparse Coding setting by creating a new representation of indoor scenes. Although CNNs highly benefited the…

Computer Vision and Pattern Recognition · Computer Science 2017-08-28 Guilherme Nascimento , Camila Laranjeira , Vinicius Braz , Anisio Lacerda , Erickson R. Nascimento

Convolutional neural network has recently achieved great success for image restoration (IR) and also offered hierarchical features. However, most deep CNN based IR models do not make full use of the hierarchical features from the original…

Computer Vision and Pattern Recognition · Computer Science 2020-01-24 Yulun Zhang , Yapeng Tian , Yu Kong , Bineng Zhong , Yun Fu