English
Related papers

Related papers: PSDNet and DPDNet: Efficient channel expansion, De…

200 papers

Dense pixelwise prediction such as semantic segmentation is an up-to-date challenge for deep convolutional neural networks (CNNs). Many state-of-the-art approaches either tackle the loss of high-resolution information due to pooling in the…

Computer Vision and Pattern Recognition · Computer Science 2018-08-07 Lingni Ma , Jörg Stückler , Tao Wu , Daniel Cremers

Deep Convolutional Neural Networks (CNNs) i.e. Residual Networks (ResNets) have been used successfully for many computer vision tasks, but are difficult to scale to 3D volumetric medical data. Memory is increasingly often the bottleneck…

Image and Video Processing · Electrical Eng. & Systems 2021-03-17 Kashu Yamazaki , Vidhiwar Singh Rathour , T. Hoang Ngan Le

Convolutional Neural Networks (CNNs) have been proven to be extremely successful at solving computer vision tasks. State-of-the-art methods favor such deep network architectures for its accuracy performance, with the cost of having massive…

Computer Vision and Pattern Recognition · Computer Science 2019-04-23 Jiahui Huang , Kshitij Dwivedi , Gemma Roig

Semantic segmentation has achieved remarkable results with high computational cost and a large number of parameters. However, real-world applications require efficient inference speed on embedded devices. Most previous works address the…

Computer Vision and Pattern Recognition · Computer Science 2020-10-22 Xinneng Yang , Yan Wu , Junqiao Zhao , Feilin Liu

In recent years, using a deep convolutional neural network (CNN) as a feature encoder (or backbone) is the most commonly observed architectural pattern in several computer vision methods, and semantic segmentation is no exception. The two…

Computer Vision and Pattern Recognition · Computer Science 2021-09-22 Venkata Satya Sai Ajay Daliparthi

We introduce blueprint separable convolutions (BSConv) as highly efficient building blocks for CNNs. They are motivated by quantitative analyses of kernel properties from trained models, which show the dominance of correlations along the…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 Daniel Haase , Manuel Amthor

We introduce Repetition-Reduction network (RRNet) for resource-constrained depth estimation, offering significantly improved efficiency in terms of computation, memory and energy consumption. The proposed method is based on…

Computer Vision and Pattern Recognition · Computer Science 2019-08-01 Sangyun Oh , Hye-Jin S. Kim , Jongeun Lee , Junmo Kim

Depthwise separable convolution has shown great efficiency in network design, but requires time-consuming training procedure with full training-set available. This paper first analyzes the mathematical relationship between regular…

Computer Vision and Pattern Recognition · Computer Science 2018-08-17 Jianbo Guo , Yuxi Li , Weiyao Lin , Yurong Chen , Jianguo Li

RGB-D semantic segmentation can be advanced with convolutional neural networks due to the availability of Depth data. Although objects cannot be easily discriminated by just the 2D appearance, with the local pixel difference and geometric…

Computer Vision and Pattern Recognition · Computer Science 2023-02-24 Jun Yang , Lizhi Bai , Yaoru Sun , Chunqi Tian , Maoyu Mao , Guorun Wang

Convolutional layers are the core building blocks of Convolutional Neural Networks (CNNs). In this paper, we propose to augment a convolutional layer with an additional depthwise convolution, where each input channel is convolved with a…

Computer Vision and Pattern Recognition · Computer Science 2020-06-23 Jinming Cao , Yangyan Li , Mingchao Sun , Ying Chen , Dani Lischinski , Daniel Cohen-Or , Baoquan Chen , Changhe Tu

In deep networks, the lost data details significantly degrade the performances of image segmentation. In this paper, we propose to apply Discrete Wavelet Transform (DWT) to extract the data details during feature map down-sampling, and…

Computer Vision and Pattern Recognition · Computer Science 2020-06-01 Qiufu Li , Linlin Shen

Some conventional transforms such as Discrete Walsh-Hadamard Transform (DWHT) and Discrete Cosine Transform (DCT) have been widely used as feature extractors in image processing but rarely applied in neural networks. However, we found that…

Computer Vision and Pattern Recognition · Computer Science 2019-07-01 Joonhyun Jeong , Sung-Ho Bae

Deep Convolutional Neural Networks (DCNNs) commonly use generic `max-pooling' (MP) layers to extract deformation-invariant features, but we argue in favor of a more refined treatment. First, we introduce epitomic convolution as a building…

Computer Vision and Pattern Recognition · Computer Science 2014-12-02 George Papandreou , Iasonas Kokkinos , Pierre-André Savalle

Designing an efficient and effective neural network has remained a prominent topic in computer vision research. Depthwise onvolution (DWConv) is widely used in efficient CNNs or ViTs, but it needs frequent memory access during inference,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-06 Haiduo Huang , Fuwei Yang , Dong Li , Ji Liu , Lu Tian , Jinzhang Peng , Pengju Ren , Emad Barsoum

Medical imaging deep learning models are often large and complex, requiring specialized hardware to train and evaluate these models. To address such issues, we propose the PocketNet paradigm to reduce the size of deep learning models by…

Image and Video Processing · Electrical Eng. & Systems 2023-11-21 Adrian Celaya , Jonas A. Actor , Rajarajeswari Muthusivarajan , Evan Gates , Caroline Chung , Dawid Schellingerhout , Beatrice Riviere , David Fuentes

This paper proposes a novel module called middle spectrum grouped convolution (MSGC) for efficient deep convolutional neural networks (DCNNs) with the mechanism of grouped convolution. It explores the broad "middle spectrum" area between…

Computer Vision and Pattern Recognition · Computer Science 2023-04-14 Zhuo Su , Jiehua Zhang , Tianpeng Liu , Zhen Liu , Shuanghui Zhang , Matti Pietikäinen , Li Liu

Modern deep neural networks have a large number of parameters, making them very hard to train. We propose DSD, a dense-sparse-dense training flow, for regularizing deep neural networks and achieving better optimization performance. In the…

Computer Vision and Pattern Recognition · Computer Science 2017-02-23 Song Han , Jeff Pool , Sharan Narang , Huizi Mao , Enhao Gong , Shijian Tang , Erich Elsen , Peter Vajda , Manohar Paluri , John Tran , Bryan Catanzaro , William J. Dally

Pansharpening is a process of fusing a high spatial resolution panchromatic image and a low spatial resolution multispectral image to create a high-resolution multispectral image. A novel single-branch, single-scale lightweight…

Computer Vision and Pattern Recognition · Computer Science 2023-07-04 Yuan Fang , Yuanzhi Cai , Lei Fan

Depthwise convolution and grouped convolution has been successfully applied to improve the efficiency of convolutional neural network (CNN). We suggest that these models can be considered as special cases of a generalized convolution…

Computer Vision and Pattern Recognition · Computer Science 2018-03-28 Dong-Qing Zhang

Deep Separable Convolutional Neural Networks (DSCNNs) have become the emerging paradigm by offering modular networks with structural sparsity in order to achieve higher accuracy with relatively lower operations and parameters. However,…

Hardware Architecture · Computer Science 2020-07-21 Mohammadreza Baharani , Ushma Sunil , Kaustubh Manohar , Steven Furgurson , Hamed Tabkhi