English
Related papers

Related papers: Source Feature Compression for Object Classificati…

200 papers

Fast and invariant feature extraction is crucial in certain computer vision applications where the computation time is constrained in both training and testing phases of the classifier. In this paper, we propose a nature-inspired…

Computer Vision and Pattern Recognition · Computer Science 2019-07-03 Ravimal Bandara , Lochandaka Ranathunga , Nor Aniza Abdullah

In this paper, we propose a set of transform-based neural network layers as an alternative to the $3\times3$ Conv2D layers in Convolutional Neural Networks (CNNs). The proposed layers can be implemented based on orthogonal transforms such…

Computer Vision and Pattern Recognition · Computer Science 2024-04-24 Hongyi Pan , Emadeldeen Hamdan , Xin Zhu , Salih Atici , Ahmet Enis Cetin

Side-scan sonar (SSS) imagery presents unique challenges in the classification of man-made objects on the seafloor due to the complex and varied underwater environments. Historically, experts have manually interpreted SSS images, relying on…

Computer Vision and Pattern Recognition · Computer Science 2024-09-19 BW Sheffield , Jeffrey Ellen , Ben Whitmore

We present a novel method of compression of deep Convolutional Neural Networks (CNNs) by weight sharing through a new representation of convolutional filters. The proposed method reduces the number of parameters of each convolutional layer…

Machine Learning · Computer Science 2020-04-13 Yingzhen Yang , Jiahui Yu , Nebojsa Jojic , Jun Huan , Thomas S. Huang

We focus on a fundamental task of detecting meaningful line structures, a.k.a. semantic line, in natural scenes. Many previous methods regard this problem as a special case of object detection and adjust existing object detectors for…

Computer Vision and Pattern Recognition · Computer Science 2021-05-04 Kai Zhao , Qi Han , Chang-Bin Zhang , Jun Xu , Ming-Ming Cheng

In single image super-resolution (SISR), given a low-resolution (LR) image, one wishes to find a high-resolution (HR) version of it which is both accurate and photo-realistic. Recently, it has been shown that there exists a fundamental…

Image and Video Processing · Electrical Eng. & Systems 2019-10-10 Xin Deng , Ren Yang , Mai Xu , Pier Luigi Dragotti

Convolutional neural networks (CNNs) are among the most widely used machine learning models for computer vision tasks, such as image classification. To improve the efficiency of CNNs, many CNNs compressing approaches have been developed.…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Mateusz Gabor , Rafał Zdunek

Model quantization enables the deployment of deep neural networks under resource-constrained devices. Vector quantization aims at reducing the model size by indexing model weights with full-precision embeddings, i.e., codewords, while the…

Computer Vision and Pattern Recognition · Computer Science 2022-12-27 Dan Liu , Xi Chen , Chen Ma , Xue Liu

An increasing share of captured images and videos are transmitted for storage and remote analysis by computer vision algorithms, rather than to be viewed by humans. Contrary to traditional standard codecs with engineered tools, neural…

Computer Vision and Pattern Recognition · Computer Science 2021-03-09 Lahiru D. Chamain , Fabien Racapé , Jean Bégaint , Akshay Pushparaja , Simon Feltman

Regional Adaptive Hierarchical Transform (RAHT) is an effective point cloud attribute compression (PCAC) method. However, its application in deep learning lacks research. In this paper, we propose an end-to-end RAHT framework for lossy PCAC…

Image and Video Processing · Electrical Eng. & Systems 2026-01-21 Chunyang Fu , Tai Qin , Shiqi Wang , Zhu Li

Pre-trained vision foundation models (VFMs) provide strong semantic representations, yet their patch-level features are inherently coarse, limiting their effectiveness on tasks requiring fine-grained localization, dense prediction, and…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Wentong Li , Zhiyuan Qi , Zichen Zhao , Kai Zhang , Lei Zhang

In this paper, we contend that the objective of representation learning is to compress and transform the distribution of the data, say sets of tokens, towards a mixture of low-dimensional Gaussian distributions supported on incoherent…

Machine Learning · Computer Science 2023-06-05 Yaodong Yu , Sam Buchanan , Druv Pai , Tianzhe Chu , Ziyang Wu , Shengbang Tong , Benjamin D. Haeffele , Yi Ma

Deep convolutional neural networks (CNNs) are the backbone of state-of-art semantic image segmentation systems. Recent work has shown that complementing CNNs with fully-connected conditional random fields (CRFs) can significantly enhance…

Computer Vision and Pattern Recognition · Computer Science 2016-06-03 Liang-Chieh Chen , Jonathan T. Barron , George Papandreou , Kevin Murphy , Alan L. Yuille

In this paper, we introduce HoughToRadon Transform layer, a novel layer designed to improve the speed of neural networks incorporated with Hough Transform to solve semantic image segmentation problems. By placing it after a Hough Transform…

Computer Vision and Pattern Recognition · Computer Science 2024-02-06 Alexandra Zhabitskaya , Alexander Sheshkus , Vladimir L. Arlazarov

While Convolutional Neural Networks (CNNs) excel at learning complex latent-space representations, their over-parameterization can lead to overfitting and reduced performance, particularly with limited data. This, alongside their high…

Computer Vision and Pattern Recognition · Computer Science 2024-01-17 Manish Sharma , Jamison Heard , Eli Saber , Panos P. Markopoulos

In this paper, we design a new class of high-efficiency deep joint source-channel coding methods to achieve end-to-end video transmission over wireless channels. The proposed methods exploit nonlinear transform and conditional coding…

Computer Vision and Pattern Recognition · Computer Science 2022-11-03 Sixian Wang , Jincheng Dai , Zijian Liang , Kai Niu , Zhongwei Si , Chao Dong , Xiaoqi Qin , Ping Zhang

Recently, many neural network-based image compression methods have shown promising results superior to the existing tool-based conventional codecs. However, most of them are often trained as separate models for different target bit rates,…

Image and Video Processing · Electrical Eng. & Systems 2022-11-09 Jooyoung Lee , Seyoon Jeong , Munchurl Kim

Hyperspectral images (HSI) consist of rich spatial and spectral information, which can potentially be used for several applications. However, noise, band correlations and high dimensionality restrict the applicability of such data. This is…

Computer Vision and Pattern Recognition · Computer Science 2024-10-28 Aditya Challa , Sravan Danda , B. S. Daya Sagar , Laurent Najman

Overparameterized models have proven to be powerful tools for solving various machine learning tasks. However, overparameterization often leads to a substantial increase in computational and memory costs, which in turn requires extensive…

Machine Learning · Computer Science 2024-03-13 Soo Min Kwon , Zekai Zhang , Dogyoon Song , Laura Balzano , Qing Qu

Image recognition tasks that involve identifying parts of an object or the contents of a vessel can be viewed as a hierarchical problem, which can be solved by initial recognition of the main object, followed by recognition of its parts or…

Computer Vision and Pattern Recognition · Computer Science 2017-10-17 Sagi Eppel