检索结果-内蒙古大学图书馆

Bridge the vision gap from field to command: A deep learning network enhancing illumination and details

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Jiang, Zhuqing Liu, Chang Wang, Ya'nan Li, Kai Men, Aidong Wang, Haiying Luo, Haiyong Beijing University of Posts and Telecommunications China Beijing Key Laboratory of Network System and Network Culture China Institute of Computing Technology Chinese Academy of Sciences China

With the goal of tuning up the brightness, low-light image enhancement enjoys numerous applications, such as surveillance, remote sensing and computational photography. Images captured under low-light conditions often suffer from poor visibility and blur. Solely brightening the dark regions will inevitably amplify the blur, thus may lead to detail loss. In this paper, we propose a simple yet effective two-stream framework named NEID to tune up the brightness and enhance the details simultaneously without introducing many computational costs. Precisely, the proposed method consists of three parts: Light Enhancement (LE), Detail Refinement (DR) and Feature Fusing (FF) module, which can aggregate composite features oriented to multiple tasks based on channel attention mechanism. Extensive experiments conducted on several benchmark datasets demonstrate the efficacy of our method and its superiority over state-of-the-art methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Luminance

Size-Invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Feiran Xu, Qianqian Bao, Shilong Yang, Zhiyong Cong, Runmin Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Sun Yat-Sen University Shenzhen Campus China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

Privileged Anatomical and Protocol Discrimination in Trackerless 3D Ultrasound Reconstruction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Qi Shen, Ziyi Li, Qian Barratt, Dean C. Dowrick, Thomas Clarkson, Matthew J. Vercauteren, Tom Hu, Yipeng Centre for Medical Image Computing Wellcome/EPSRC Centre for Interventional and Surgical Sciences Department of Medical Physics and Biomedical Engineering University College London London United Kingdom State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China School of Biomedical Engineering & Imaging Sciences King’s College London London United Kingdom

Three-dimensional (3D) freehand ultrasound (US) reconstruction without using any additional external tracking device has seen recent advances with deep neural networks (DNNs). In this paper, we first investigated two identified contributing factors of the learned inter-frame correlation that enable the DNN-based reconstruction: anatomy and protocol. We propose to incorporate the ability to represent these two factors - readily available during training - as the privileged information to improve existing DNN-based methods. This is implemented in a new multitask method, where the anatomical and protocol discrimination are used as auxiliary tasks. We further develop a differentiable network architecture to optimise the branching location of these auxiliary tasks, which controls the ratio between shared and task-specific network parameters, for maximising the benefits from the two auxiliary tasks. Experimental results, on a dataset with 38 forearms of 19 volunteers acquired with 6 different scanning protocols, show that 1) both anatomical and protocol variances are enabling factors for DNN-based US reconstruction;2) learning how to discriminate different subjects (anatomical variance) and predefined types of scanning paths (protocol variance) both significantly improve frame prediction accuracy, volume reconstruction overlap, accumulated tracking error and final drift, using the proposed algorithm. © 2023, CC BY.

关键词： Deep neural networks

Poisoning as a Post-Protection: Mitigating Membership Privacy Leakage From Gradient and Prediction of Federated Models

学校读者我要写书评

暂无评论

IEEE Transactions on Dependable and Secure computing 2025年

作者： Liu, Gaoyang Xu, Tianlong Yang, Yang Abdelmoniem, Ahmed M. Wang, Chen Liu, Jiangchuan Huazhong University of Science and Technology Hubei Key Laboratory of Internet of Intelligence School of Electronic Information and Communications Wuhan430074 China Simon Fraser University School of Computing Science BurnabyBCV5A 1S6 Canada Ministry of Education Key Laboratory of Intelligent Sensing System and Security China Hubei University School of Artificial Intelligence Wuhan430062 China Queen Mary University of London School of Electronic Engineering and Computer Science United Kingdom

Federated learning (FL) is a distributed learning paradigm that enables multiple clients to train a unified model without sharing their private data. However, recent works demonstrate that FL models are vulnerable to membership inference attacks (MIAs), which can infer whether a data sample was used to train a given FL model. Existing countermeasures either require far-reaching modifications of FL training process or enforce extra processing in prediction phase, yielding them unlikely to be applied well in practice. In this paper, we design a post-protection mechanism, dubbed P2-Protection, which degrades the inference performance of MIAs by simultaneously poisoning the prediction and gradient of the target FL model to reduce the privacy leakage of training data while keeping the model prediction accuracy. P2-Protection only involves one additional training round to embed the poisoned prediction and gradient into the target FL model, without requiring model retraining or training process modification. We evaluate P2-Protection and compare it with two state-of-the-art defenses against three MIAs on five realistic datasets. Experimental results show that P2-Protection outperforms the existing defenses by offering limited implement overhead and improved utility-privacy trade-off. © 2004-2012 IEEE.

关键词： Federated learning

Self-Supervised GANs with Label Augmentation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hou, Liang Shen, Huawei Cao, Qi Cheng, Xueqi Data Intelligence System Research Center Institute of Computing Technology Chinese Academy of Sciences China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Recently, transformation-based self-supervised learning has been applied to generative adversarial networks (GANs) to mitigate catastrophic forgetting in the discriminator by introducing a stationary learning environment. However, the separate self-supervised tasks in existing self-supervised GANs cause a goal inconsistent with generative modeling due to the fact that their self-supervised classifiers are agnostic to the generator distribution. To address this problem, we propose a novel self-supervised GAN that unifies the GAN task with the self-supervised task by augmenting the GAN labels (real or fake) via self-supervision of data transformation. Specifically, the original discriminator and self-supervised classifier are unified into a label-augmented discriminator that predicts the augmented labels to be aware of both the generator distribution and the data distribution under every transformation, and then provide the discrepancy between them to optimize the generator. Theoretically, we prove that the optimal generator could converge to replicate the real data distribution. Empirically, we show that the proposed method significantly outperforms previous self-supervised and data augmentation GANs on both generative modeling and representation learning across benchmark datasets. Copyright © 2021, The Authors. All rights reserved.

关键词： Generative adversarial networks

PREP: Pre-training with Temporal Elapse Inference for Popularity Prediction

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cao, Qi Shen, Huawei Liu, Yuanhao Gao, Jinhua Cheng, Xueqi Data Intelligence System Research Center Institute of Computing Technology Chinese Academy of Sciences China Cas Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Predicting the popularity of online content is a fundamental problem in various applications. One practical challenge takes roots in the varying length of observation time or prediction horizon, i.e., a good model for popularity prediction is desired to handle various prediction settings. However, most existing methods adopt a separate training paradigm for each prediction setting and the obtained model for one setting is difficult to be generalized to others, causing a great waste of computational resources and a large demand for downstream labels. To solve the above issues, we propose a novel pre-training framework for popularity prediction, namely PREP, aiming to pre-train a general representation model from the readily available unlabeled diffusion data, which can be effectively transferred into various prediction settings. We design a novel pretext task for pre-training, i.e., temporal elapse inference for two randomly sampled time slices of popularity dynamics, impelling the representation model to learn intrinsic knowledge about popularity dynamics. Experimental results conducted on two real datasets demonstrate the generalization and efficiency of the pre-training framework for different popularity prediction task settings. Copyright © 2021, The Authors. All rights reserved.

关键词： Forecasting

Measurement-Based Non-Stationary Markov Tapped Delay Line Channel Model for 5G-Railways

学校读者我要写书评

暂无评论

IEEE Antennas and Wireless Propagation Letters 2025年

作者： Zhang, Xuejian He, Ruisi Yang, Mi Ding, Jianwen Chen, Ruifeng Gao, Shuaiqi Qi, Ziyi Zhang, Zhengyu Ai, Bo Zhong, Zhangdui Beijing Jiaotong University State Key Laboratory of Advanced Rail Autonomous Operation The School of Electronics and Information Engineering The Frontiers Science Center for Smart High-speed Railway System Beijing100044 China Beijing Jiaotong University School of Electronics and Information Engineering Beijing100044 China Henan High Speed Railway Operation and Maintenance Engineering Research Center Zhengzhou451460 China China Academy of Railway Sciences Corporation Ltd. Institute of Computing Technology Beijing100081 China

5 G for Railways (5G-R) is globally recognized as a promising next-generation railway communication system designed to meet increasing demands. Channel modeling serves as foundation for communication system design, with tapped delay line (TDL) models widely utilized in system simulations due to their simplicity and practicality and serves as a crucial component of various standards like 3GPP. However, existing TDL models applicable to 5G-R systems are limited. Most fail to capture non-stationarity, a critical characteristic of railway communications, while others are unsuitable for the specific frequency bands and bandwidths of 5G-R. In this paper, a channel measurement campaign for 5G-R dedicated network is carried out, resulting in a measurement-based 5-tap TDL model utilizing a first-order two-state Markov chain to represent channel non-stationarity. key model parameters, including number of taps, statistical distribution of amplitude, phase and Doppler shift, and state transition probability matrix, are extracted. The correlation between tap amplitudes is also obtained. Finally, the accuracy of model is validated through comparisons with measurement data and 3GPP model. These findings are expected to offer valuable insights for design and link-level simulation of 5G-R systems. © 2025 IEEE.

关键词： Markov chains

CodeEnhance: A Codebook-Driven Approach for Low-Light Image Enhancement

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Xu Hou, XianXu Lai, Zhihui Zhou, Jie Zhang, Ya-Nan Pedrycz, Witold Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China The Department of Electrical & Computer Engineering University of Alberta University of Alberta Canada

Low-light image enhancement (LLIE) aims to improve low-illumination images. However, existing methods face two challenges: (1) uncertainty in restoration from diverse brightness degradations;(2) loss of texture and color information caused by noise suppression and light enhancement. In this paper, we propose a novel enhancement approach, CodeEnhance, by leveraging quantized priors and image refinement to address these challenges. In particular, we reframe LLIE as learning an image-to-code mapping from low-light images to discrete codebook, which has been learned from high-quality images. To enhance this process, a Semantic Embedding Module (SEM) is introduced to integrate semantic information with low-level features, and a Codebook Shift (CS) mechanism, designed to adapt the pre-learned codebook to better suit the distinct characteristics of our low-light dataset. Additionally, we present an Interactive Feature Transformation (IFT) module to refine texture and color information during image reconstruction, allowing for interactive enhancement based on user preferences. Extensive experiments on both real-world and synthetic benchmarks demonstrate that the incorporation of prior knowledge and controllable information transfer significantly enhances LLIE performance in terms of quality and fidelity. The proposed CodeEnhance exhibits superior robustness to various degradations, including uneven illumination, noise, and color distortion. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

Ultra-Fast Mini License Plate Recognition system Based-on Vision Processing Unit 20

学校读者我要写书评

暂无评论

Ultra-Fast Mini License Plate Recognition System Based-on Vi...

Proceedings of the 2020 2nd International Conference on Big-data Service and Intelligent Computation

作者： Junhui Wang Shuangyin Ren Jiezhong He Xiaolan Ji Diqing Huang College of Computer National University of Defense Technology and State Key Laboratory of Mathematical Engineering and Advanced Computing China National Key Laboratory of Science and Technology on Information System Security Institute of Systems Engineering Academy of Military Science College of Computer National University of Defense Technology

ISBN: (纸本)9781450388399

As more embedded environments need license plate recognition systems, how to recognize car plates with high speed/accuracy and low energy has become an important and challenging problem. In this paper, we propose a ultra-Fast miNi (FaNi) license plate recognition (LPR) system. The FaNi system are divided into one training sub-system and one inference sub-system. The former are used to get some offline features; then, the latter is deployed online to recognize license numbers with nearly real-time speed. The inference system is comprised of the vision processing unit (VPU) and the display unit. These two parts are both implemented with hardware logic. Experiments show that the FaNi system can obtain high accuracy and high speed with low resource cost.

关键词： VPU Plate Recognition system FPGA