English
Related papers

Related papers: UniRepLKNet: A Universal Perception Large-Kernel C…

200 papers

Despite the tremendous success in computer vision, deep convolutional networks suffer from serious computation costs and redundancies. Although previous works address this issue by enhancing diversities of filters, they have not considered…

Computer Vision and Pattern Recognition · Computer Science 2022-01-19 Yang Hu , Guihua Wen , Mingnan Luo , Dan Dai , Wenming Cao , Zhiwen Yu , Wendy Hall

Fully convolutional U-shaped neural networks have largely been the dominant approach for pixel-wise image segmentation. In this work, we tackle two defects that hinder their deployment in real-world applications: 1) Predictions lack…

Computer Vision and Pattern Recognition · Computer Science 2021-06-29 Martin Ferianc , Divyansh Manocha , Hongxiang Fan , Miguel Rodrigues

We present an analysis of three possible strategies for exploiting the power of existing convolutional neural networks (ConvNets) in different scenarios from the ones they were trained: full training, fine tuning, and using ConvNets as…

Computer Vision and Pattern Recognition · Computer Science 2016-11-08 Keiller Nogueira , Otávio A. B. Penatti , Jefersson A. dos Santos

Large-scale supervised pretraining is rapidly reshaping 3D medical image segmentation. However, existing efforts focus primarily on increasing dataset size and overlook the question of whether the backbone network is an effective…

Image and Video Processing · Electrical Eng. & Systems 2025-12-22 Saikat Roy , Yannick Kirchhoff , Constantin Ulrich , Maximillian Rokuss , Tassilo Wald , Fabian Isensee , Klaus Maier-Hein

Despite the effectiveness of Convolutional Neural Networks (CNNs) for image classification, our understanding of the relationship between shape of convolution kernels and learned representations is limited. In this work, we explore and…

Computer Vision and Pattern Recognition · Computer Science 2016-11-30 Zhun Sun , Mete Ozay , Takayuki Okatani

High-resolution representations are important for vision-based robotic grasping problems. Existing works generally encode the input images into low-resolution representations via sub-networks and then recover high-resolution…

Robotics · Computer Science 2022-09-19 Zhangli Zhou , Shaochen Wang , Ziyang Chen , Mingyu Cai , Zhen Kan

We propose unitary group convolutions (UGConvs), a building block for CNNs which compose a group convolution with unitary transforms in feature space to learn a richer set of representations than group convolution alone. UGConvs generalize…

Machine Learning · Computer Science 2019-04-10 Ritchie Zhao , Yuwei Hu , Jordan Dotzel , Christopher De Sa , Zhiru Zhang

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

Deep networks have achieved huge successes in application domains like object and face recognition. The performance gain is attributed to different facets of the network architecture such as: depth of the convolutional layers, activation…

Computer Vision and Pattern Recognition · Computer Science 2019-05-03 Chollette C. Olisah , Lyndon Smith

Conventional neural architectures for sequential data present important limitations. Recurrent networks suffer from exploding and vanishing gradients, small effective memory horizons, and must be trained sequentially. Convolutional networks…

Machine Learning · Computer Science 2022-03-18 David W. Romero , Anna Kuzina , Erik J. Bekkers , Jakub M. Tomczak , Mark Hoogendoorn

This paper revives Densely Connected Convolutional Networks (DenseNets) and reveals the underrated effectiveness over predominant ResNet-style architectures. We believe DenseNets' potential was overlooked due to untouched training methods…

Computer Vision and Pattern Recognition · Computer Science 2024-08-08 Donghyun Kim , Byeongho Heo , Dongyoon Han

Performant Convolutional Neural Network (CNN) architectures must be tailored to specific tasks in order to consider the length, resolution, and dimensionality of the input data. In this work, we tackle the need for problem-specific CNN…

Computer Vision and Pattern Recognition · Computer Science 2023-04-18 David M. Knigge , David W. Romero , Albert Gu , Efstratios Gavves , Erik J. Bekkers , Jakub M. Tomczak , Mark Hoogendoorn , Jan-Jakob Sonke

Convolutional Neural Networks have been the backbone of recent rapid progress in Single-Image Super-Resolution. However, existing networks are very deep with many network parameters, thus having a large memory footprint and being…

Computer Vision and Pattern Recognition · Computer Science 2018-04-24 George Seif , Dimitrios Androutsos

To efficiently extract spatiotemporal features of video for action recognition, most state-of-the-art methods integrate 1D temporal convolution into a conventional 2D CNN backbone. However, they all exploit 1D temporal convolution of fixed…

Computer Vision and Pattern Recognition · Computer Science 2020-01-28 Kaiyu Shan , Yongtao Wang , Zhuoying Wang , Tingting Liang , Zhi Tang , Ying Chen , Yangyan Li

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we…

Machine Learning · Computer Science 2020-01-09 Gao Huang , Zhuang Liu , Geoff Pleiss , Laurens van der Maaten , Kilian Q. Weinberger

Text-to-image generation has advanced rapidly with diffusion models, progressing from CLIP and T5 conditioning to unified systems where a single LLM backbone handles both visual understanding and generation. Despite the architectural…

Computer Vision and Pattern Recognition · Computer Science 2026-05-06 Sucheng Ren , Chen Chen , Zhenbang Wang , Liangchen Song , Xiangxin Zhu , Alan Yuille , Liang-Chieh Chen , Jiasen Lu

Deep convolutional neural networks, assisted by architectural design strategies, make extensive use of data augmentation techniques and layers with a high number of feature maps to embed object transformations. That is highly inefficient…

Computer Vision and Pattern Recognition · Computer Science 2021-12-21 Vittorio Mazzia , Francesco Salvetti , Marcello Chiaberge

A multitude of imaging and vision tasks have seen recently a major transformation by deep learning methods and in particular by the application of convolutional neural networks. These methods achieve impressive results, even for…

Computer Vision and Pattern Recognition · Computer Science 2018-11-30 Simon Arridge , Andreas Hauptmann

In this work, we investigate the capability of generating images from pre-trained diffusion models at much higher resolutions than the training image sizes. In addition, the generated images should have arbitrary image aspect ratios. When…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Yingqing He , Shaoshu Yang , Haoxin Chen , Xiaodong Cun , Menghan Xia , Yong Zhang , Xintao Wang , Ran He , Qifeng Chen , Ying Shan

Deep Convolutional Neural Networks (CNNs) are capable of learning unprecedentedly effective features from images. Some researchers have struggled to enhance the parameters' efficiency using grouped convolution. However, the relation between…

Computer Vision and Pattern Recognition · Computer Science 2017-06-22 Yujia Chen , Ce Li