English
Related papers

Related papers: Towards CNN map representation and compression for…

200 papers

Large CNNs have delivered impressive performance in various computer vision applications. But the storage and computation requirements make it problematic for deploying these models on mobile devices. Recently, tensor decompositions have…

Machine Learning · Computer Science 2016-02-16 Cheng Tai , Tong Xiao , Yi Zhang , Xiaogang Wang , Weinan E

It is well known that Convolutional Neural Networks (CNNs) have significant redundancy in their filter weights. Various methods have been proposed in the literature to compress trained CNNs. These include techniques like pruning weights,…

Machine Learning · Computer Science 2019-06-12 Muhammad Tayyab , Abhijit Mahalanobis

We propose an efficient and straightforward method for compressing deep convolutional neural networks (CNNs) that uses basis filters to represent the convolutional layers, and optimizes the performance of the compressed network directly in…

Computer Vision and Pattern Recognition · Computer Science 2021-05-24 Muhammad Tayyab , Fahad Ahmad Khan , Abhijit Mahalanobis

We propose a novel Convolutional Neural Network (CNN) compression algorithm based on coreset representations of filters. We exploit the redundancies extant in the space of CNN weights and neuronal activations (across samples) in order to…

Computer Vision and Pattern Recognition · Computer Science 2018-07-27 Abhimanyu Dubey , Moitreya Chatterjee , Narendra Ahuja

This paper investigates how working of Convolutional Neural Network (CNN) can be explained through visualization in the context of machine perception of autonomous vehicles. We visualize what type of features are extracted in different…

Computer Vision and Pattern Recognition · Computer Science 2020-07-16 Abhishek Mukhopadhyay , Imon Mukherjee , Pradipta Biswas

Path loss prediction is a beneficial tool for efficient use of the radio frequency spectrum. Building on prior research on high-resolution map-based path loss models, this paper studies convolutional neural network input representations in…

Machine Learning · Computer Science 2026-02-05 Ryan G. Dempsey , Jonathan Ethier , Halim Yanikomeroglu

This paper proposes a new image-based localization framework that explicitly localizes the camera/robot by fusing Convolutional Neural Network (CNN) and sequential images' geometric constraints. The camera is localized using a single or few…

Computer Vision and Pattern Recognition · Computer Science 2022-01-06 Jingwei Song , Mitesh Patel , Maani Ghaffari

Deep neural networks have achieved strong performance in image classification tasks due to their ability to learn complex patterns from high-dimensional data. However, their large computational and memory requirements often limit deployment…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Sai Shi

This paper presents a novel approach for video-based person re-identification using multiple Convolutional Neural Networks (CNNs). Unlike previous work, we intend to extract a compact yet discriminative appearance representation from…

Computer Vision and Pattern Recognition · Computer Science 2019-09-23 Wei Zhang , Shengnan Hu , Kan Liu , Zhengjun Zha

In recent years, convolutional neural networks (CNNs) have shown great performance in various fields such as image classification, pattern recognition, and multi-media compression. Two of the feature properties, local connectivity and…

Machine Learning · Computer Science 2018-07-24 Qianru Zhang , Meng Zhang , Tinghuan Chen , Zhifei Sun , Yuzhe Ma , Bei Yu

Convolutional Neural Network (CNN)-based machine learning systems have made breakthroughs in feature extraction and image recognition tasks in two dimensions (2D). Although there is significant ongoing work to apply CNN technology to…

Computer Vision and Pattern Recognition · Computer Science 2018-02-26 Thomas Corcoran , Rafael Zamora-Resendiz , Xinlian Liu , Silvia Crivelli

In this paper, we propose a novel convolutional neural network (CNN) architecture considering both local and global features for image enhancement. Most conventional image enhancement methods, including Retinex-based methods, cannot restore…

Image and Video Processing · Electrical Eng. & Systems 2019-05-09 Yuma Kinoshita , Hitoshi Kiya

This work is concerned with a representation of shapes that disentangles fine, local and possibly repeating geometry, from global, coarse structures. Achieving such disentanglement leads to two unrelated advantages: i) a significant…

Computer Vision and Pattern Recognition · Computer Science 2022-04-06 Luca Morreale , Noam Aigerman , Paul Guerrero , Vladimir G. Kim , Niloy J. Mitra

The modern convolutional neural networks although achieve great results in solving complex computer vision tasks still cannot be effectively used in mobile and embedded devices due to the strict requirements for computational complexity,…

Computer Vision and Pattern Recognition · Computer Science 2020-06-17 Nikolay Kozyrskiy , Anh-Huy Phan

In the realm of image processing and computer vision (CV), machine learning (ML) architectures are widely applied. Convolutional neural networks (CNNs) solve a wide range of image processing issues and can solve image compression problem.…

Image and Video Processing · Electrical Eng. & Systems 2022-01-25 Sonain Jamil , Md. Jalil Piran , MuhibUrRahman

Owing to flexible architectures of deep convolutional neural networks (CNNs), CNNs are successfully used for image denoising. However, they suffer from the following drawbacks: (i) deep network architecture is very difficult to train. (ii)…

Computer Vision and Pattern Recognition · Computer Science 2019-03-05 Chunwei Tian , Yong Xu , Lunke Fei , Junqian Wang , Jie Wen , Nan Luo

For crowded scenes, the accuracy of object-based computer vision methods declines when the images are low-resolution and objects have severe occlusions. Taking counting methods for example, almost all the recent state-of-the-art counting…

Computer Vision and Pattern Recognition · Computer Science 2018-06-14 Di Kang , Zheng Ma , Antoni B. Chan

Convolutional Neural Network (CNN) features have been successfully employed in recent works as an image descriptor for various vision tasks. But the inability of the deep CNN features to exhibit invariance to geometric transformations and…

Computer Vision and Pattern Recognition · Computer Science 2015-04-27 Konda Reddy Mopuri , R. Venkatesh Babu

In this paper we present a methodology that uses convolutional neural networks (CNNs) for segmentation by iteratively growing predicted mask regions in each coordinate direction. The CNN is used to predict class probability scores in a…

Image and Video Processing · Electrical Eng. & Systems 2020-09-25 John Lagergren , Erica Rutter , Kevin Flores

In this paper, we compress convolutional neural network (CNN) weights post-training via transform quantization. Previous CNN quantization techniques tend to ignore the joint statistics of weights and activations, producing sub-optimal CNN…

Computer Vision and Pattern Recognition · Computer Science 2021-11-09 Sean I. Young , Wang Zhe , David Taubman , Bernd Girod