English
Related papers

Related papers: RepVGG: Making VGG-style ConvNets Great Again

200 papers

Convolutional Neural Networks (CNNs) have become indispensable for solving machine learning tasks in speech recognition, computer vision, and other areas that involve high-dimensional data. A CNN filters the input feature using a network…

Machine Learning · Computer Science 2020-02-13 Jonathan Ephrath , Moshe Eliasof , Lars Ruthotto , Eldad Haber , Eran Treister

Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-art in semantic segmentation. Our key…

Computer Vision and Pattern Recognition · Computer Science 2015-03-10 Jonathan Long , Evan Shelhamer , Trevor Darrell

We introduce MinConvLSTM and MinConvGRU, two novel spatiotemporal models that combine the spatial inductive biases of convolutional recurrent networks with the training efficiency of minimal, parallelizable RNNs. Our approach extends the…

Machine Learning · Computer Science 2025-08-06 Coşku Can Horuz , Sebastian Otte , Martin V. Butz , Matthias Karlbauer

Recent years have witnessed remarkable advances in spatiotemporal predictive learning, with methods incorporating auxiliary inputs, complex neural architectures, and sophisticated training strategies. While SimVP has introduced a simpler,…

Machine Learning · Computer Science 2024-12-13 Cheng Tan , Zhangyang Gao , Siyuan Li , Stan Z. Li

We propose a lightweight CPU network based on the MKLDNN acceleration strategy, named PP-LCNet, which improves the performance of lightweight models on multiple tasks. This paper lists technologies which can improve network accuracy while…

Computer Vision and Pattern Recognition · Computer Science 2021-10-01 Cheng Cui , Tingquan Gao , Shengyu Wei , Yuning Du , Ruoyu Guo , Shuilong Dong , Bin Lu , Ying Zhou , Xueying Lv , Qiwen Liu , Xiaoguang Hu , Dianhai Yu , Yanjun Ma

In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks. Given a trained CNN model, we propose an iterative two-step algorithm to effectively prune each layer, by a LASSO regression…

Computer Vision and Pattern Recognition · Computer Science 2022-11-16 Yihui He

The accuracy of deep convolutional neural networks (CNNs) generally improves when fueled with high resolution images. However, this often comes at a high computational cost and high memory footprint. Inspired by the fact that not all…

Computer Vision and Pattern Recognition · Computer Science 2020-10-13 Yulin Wang , Kangchen Lv , Rui Huang , Shiji Song , Le Yang , Gao Huang

Recent studies in image classification have demonstrated a variety of techniques for improving the performance of Convolutional Neural Networks (CNNs). However, attempts to combine existing techniques to create a practical model are still…

Computer Vision and Pattern Recognition · Computer Science 2020-03-16 Jungkyu Lee , Taeryun Won , Tae Kwan Lee , Hyemin Lee , Geonmo Gu , Kiho Hong

We design a family of image classification architectures that optimize the trade-off between accuracy and efficiency in a high-speed regime. Our work exploits recent findings in attention-based architectures, which are competitive on highly…

Computer Vision and Pattern Recognition · Computer Science 2021-05-07 Ben Graham , Alaaeldin El-Nouby , Hugo Touvron , Pierre Stock , Armand Joulin , Hervé Jégou , Matthijs Douze

Two-stream Convolutional Networks (ConvNets) have shown strong performance for human action recognition in videos. Recently, Residual Networks (ResNets) have arisen as a new technique to train extremely deep architectures. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2016-11-08 Christoph Feichtenhofer , Axel Pinz , Richard P. Wildes

Depth completion deals with the problem of recovering dense depth maps from sparse ones, where color images are often used to facilitate this task. Recent approaches mainly focus on image guided learning frameworks to predict dense depth.…

Computer Vision and Pattern Recognition · Computer Science 2022-07-14 Zhiqiang Yan , Kun Wang , Xiang Li , Zhenyu Zhang , Jun Li , Jian Yang

In this paper, we propose a novel behavior model for wideband PAs using a real-valued time-delay convolutional neural network (RVTDCNN). The input data of the model are sorted and arranged as the graph composed of the in-phase and…

Signal Processing · Electrical Eng. & Systems 2020-05-21 Xin Hu , Zhijun Liu , Xiaofei Yu , Yulong Zhao , Wenhua Chen , Biao Hu , Xuekun Du , Xiang Li , Mohamed Helaoui , Weidong Wang , Fadhel M. Ghannouchi

Deep convolutional neural networks take GPU days of compute time to train on large data sets. Pedestrian detection for self driving cars requires very low latency. Image recognition for mobile phones is constrained by limited processing…

Neural and Evolutionary Computing · Computer Science 2015-11-11 Andrew Lavin , Scott Gray

Residual neural networks (ResNets) are a promising class of deep neural networks that have shown excellent performance for a number of learning tasks, e.g., image classification and recognition. Mathematically, ResNet architectures can be…

Optimization and Control · Mathematics 2019-07-26 S. Günther , L. Ruthotto , J. B. Schroder , E. C. Cyr , N. R. Gauger

Deep Neural Networks (DNNs) have achieved im- pressive accuracy in many application domains including im- age classification. Training of DNNs is an extremely compute- intensive process and is solved using variants of the stochastic…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-11-03 Sameer Kumar , Dheeraj Sreedhar , Vaibhav Saxena , Yogish Sabharwal , Ashish Verma

We propose a general method to train a single convolutional neural network which is capable of switching image resolutions at inference. Thus the running speed can be selected to meet various computational resource limits. Networks trained…

Computer Vision and Pattern Recognition · Computer Science 2020-11-10 Yikai Wang , Fuchun Sun , Duo Li , Anbang Yao

Integer-arithmetic-only networks have been demonstrated effective to reduce computational cost and to ensure cross-platform consistency. However, previous works usually report a decline in the inference accuracy when converting well-trained…

Computer Vision and Pattern Recognition · Computer Science 2020-06-23 Hengrui Zhao , Dong Liu , Houqiang Li

While parameter efficient tuning (PET) methods have shown great potential with transformer architecture on Natural Language Processing (NLP) tasks, their effectiveness with large-scale ConvNets is still under-studied on Computer Vision (CV)…

Computer Vision and Pattern Recognition · Computer Science 2024-04-15 Hao Chen , Ran Tao , Han Zhang , Yidong Wang , Xiang Li , Wei Ye , Jindong Wang , Guosheng Hu , Marios Savvides

Convolutional Neural Networks (CNNs) have demonstrated remarkable ability throughout the field of computer vision. However, CNN inference requires a large number of arithmetic operations, making them expensive to deploy in hardware. Current…

Computer Vision and Pattern Recognition · Computer Science 2024-04-10 Neelesh Gupta , Narayanan Kannan , Pengmiao Zhang , Viktor Prasanna

In this work, we propose a new deep learning model for Genomic Prediction (GP), which involves correlating genotypic data with phenotypic. The genotypes are typically fed as a sequence of characters to the 1D-Convolution Neural Network…

Machine Learning · Computer Science 2026-03-03 Kuldeep Pathak , Kapil Ahuja , Eric de Sturler