English
Related papers

Related papers: Tensor decomposition to Compress Convolutional Lay…

200 papers

Intrinsic image decomposition is an important and long-standing computer vision problem. Given an input image, recovering the physical scene properties is ill-posed. Several physically motivated priors have been used to restrict the…

Computer Vision and Pattern Recognition · Computer Science 2022-09-27 Zongji Wang , Yunfei Liu , Feng Lu

Convolutions are the fundamental building block of CNNs. The fact that their weights are spatially shared is one of the main reasons for their widespread use, but it also is a major limitation, as it makes convolutions content agnostic. We…

Computer Vision and Pattern Recognition · Computer Science 2019-04-12 Hang Su , Varun Jampani , Deqing Sun , Orazio Gallo , Erik Learned-Miller , Jan Kautz

In this paper, we introduce deep learning technology to tackle two traditional low-level image processing problems, companding and inverse halftoning. We make two main contributions. First, to the best knowledge of the authors, this is the…

Computer Vision and Pattern Recognition · Computer Science 2017-07-24 Xianxu Hou , Guoping Qiu

This paper proposes a novel deep subspace clustering approach which uses convolutional autoencoders to transform input images into new representations lying on a union of linear subspaces. The first contribution of our work is to insert…

Computer Vision and Pattern Recognition · Computer Science 2020-01-24 Mohsen Kheirandishfard , Fariba Zohrizadeh , Farhad Kamangar

Compressing convolutional neural networks (CNNs) is essential for transferring the success of CNNs to a wide variety of applications to mobile devices. In contrast to directly recognizing subtle weights or filters as redundant in a given…

Machine Learning · Statistics 2017-07-26 Yunhe Wang , Chang Xu , Jiayan Qiu , Chao Xu , Dacheng Tao

Tensors have broad applications in neuroimaging, data mining, digital marketing, etc. CANDECOMP/PARAFAC (CP) tensor decomposition can effectively reduce the number of parameters to gain dimensionality-reduction and thus plays a key role in…

Statistics Theory · Mathematics 2023-11-23 Qiushi Bu , Hua Liang , Xinyu Zhang , Jiahui Zou

The purpose of feature extraction on convolutional neural networks is to reuse deep representations learnt for a pre-trained model to solve a new, potentially unrelated problem. However, raw feature extraction from all layers is unfeasible…

Neural and Evolutionary Computing · Computer Science 2019-11-11 Victor Gimenez-Abalos , Armand Vilalta , Dario Garcia-Gasulla , Jesus Labarta , Eduard Ayguadé

This paper shows that it is possible to train large and deep convolutional neural networks (CNN) for JPEG compression artifacts reduction, and that such networks can provide significantly better reconstruction quality compared to previously…

Computer Vision and Pattern Recognition · Computer Science 2016-05-03 Pavel Svoboda , Michal Hradis , David Barina , Pavel Zemcik

With the rapid development of machine vision technology in recent years, many researchers have begun to focus on feature compression that is better suited for machine vision tasks. The target of feature compression is deep features, which…

Computer Vision and Pattern Recognition · Computer Science 2024-05-31 Lei Xiong , Xin Luo , Zihao Wang , Chaofan He , Shuyuan Zhu , Bing Zeng

In this work, we propose a simple but effective channel pruning framework called Progressive Channel Pruning (PCP) to accelerate Convolutional Neural Networks (CNNs). In contrast to the existing channel pruning methods that prune channels…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Jinyang Guo , Weichen Zhang , Wanli Ouyang , Dong Xu

Convolutional neural networks (CNNs) have gained widespread usage across various fields such as weather forecasting, computer vision, autonomous driving, and medical image analysis due to its exceptional ability to extract spatial…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Alifu Xiafukaiti , Devanshu Garg , Aruto Hosaka , Koichi Yanagisawa , Yuichiro Minato , Tsuyoshi Yoshida

A novel energy-efficient edge computing paradigm is proposed for real-time deep learning-based image upsampling applications. State-of-the-art deep learning solutions for image upsampling are currently trained using either resize or…

Computer Vision and Pattern Recognition · Computer Science 2021-07-27 Ian Colbert , Ken Kreutz-Delgado , Srinjoy Das

Tensor decomposition is an important technique for capturing the high-order interactions among multiway data. Multi-linear tensor composition methods, such as the Tucker decomposition and the CANDECOMP/PARAFAC (CP), assume that the complex…

Machine Learning · Statistics 2016-11-04 Bin Liu , Zenglin Xu , Yingming Li

We propose methodologies to train highly accurate and efficient deep convolutional neural networks (CNNs) for image super resolution (SR). A cascade training approach to deep learning is proposed to improve the accuracy of the neural…

Computer Vision and Pattern Recognition · Computer Science 2017-11-15 Haoyu Ren , Mostafa El-Khamy , Jungwon Lee

Tensor-valued data arise naturally in neuroimaging, genomics, climate science, and spatiotemporal networks, where multilinear dependencies across modes carry information that is destroyed under vectorization. Existing approaches either…

Machine Learning · Statistics 2026-05-20 Elynn Chen , Jiayu Li , Zheshi Zheng , Jian Pei

We propose a novel semantic segmentation algorithm by learning a deconvolution network. We learn the network on top of the convolutional layers adopted from VGG 16-layer net. The deconvolution network is composed of deconvolution and…

Computer Vision and Pattern Recognition · Computer Science 2015-05-19 Hyeonwoo Noh , Seunghoon Hong , Bohyung Han

Convolutional neural networks typically consist of many convolutional layers followed by one or more fully connected layers. While convolutional layers map between high-order activation tensors, the fully connected layers operate on…

Machine Learning · Computer Science 2020-07-22 Jean Kossaifi , Zachary C. Lipton , Arinbjorn Kolbeinsson , Aran Khanna , Tommaso Furlanello , Anima Anandkumar

Deep convolutional neural networks have proven to be well suited for image classification applications. However, if there is distortion in the image, the classification accuracy can be significantly degraded, even with state-of-the-art…

Computer Vision and Pattern Recognition · Computer Science 2019-02-15 Minho Ha , Younghoon Byeon , Youngjoo Lee , Sunggu Lee

We propose a Deep Texture Encoding Network (Deep-TEN) with a novel Encoding Layer integrated on top of convolutional layers, which ports the entire dictionary learning and encoding pipeline into a single model. Current methods build from…

Computer Vision and Pattern Recognition · Computer Science 2016-12-12 Hang Zhang , Jia Xue , Kristin Dana

Many state-of-the-art computer vision algorithms use large scale convolutional neural networks (CNNs) as basic building blocks. These CNNs are known for their huge number of parameters, high redundancy in weights, and tremendous computing…

Computer Vision and Pattern Recognition · Computer Science 2018-01-24 Qiangui Huang , Kevin Zhou , Suya You , Ulrich Neumann