检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Liu, Jun Li, Qing Cao, Rui Tang, Wenming Qiu, Guoping College of Electronics and Information Engineering Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of Computer Science University of Nottingham United Kingdom

Predicting depth from a single image is an attractive research topic since it provides one more dimension of information to enable machines to better perceive the world. Recently, deep learning has emerged as an effective approach to monocular depth estimation. As obtaining labeled data is costly, there is a recent trend to move from supervised learning to unsupervised learning to obtain monocular depth. However, most unsupervised learning methods capable of achieving high depth prediction accuracy will require a deep network architecture which will be too heavy and complex to run on embedded devices with limited storage and memory spaces. To address this issue, we propose a new powerful network with a recurrent module to achieve the capability of a deep network while at the same time maintaining an extremely lightweight size for real-time high performance unsupervised monocular depth prediction from video sequences. Besides, a novel efficient upsample block is proposed to fuse the features from the associated encoder layer and recover the spatial size of features with the small number of model parameters. We validate the effectiveness of our approach via extensive experiments on the KITTI dataset. Our new model can run at a speed of about 110 frames per second (fps) on a single GPU, 37 fps on a single CPU, and 2 fps on a Raspberry Pi 3. Moreover, it achieves higher depth accuracy with nearly 33 times fewer model parameters than state-of-the-art models. To the best of our knowledge, this work is the first extremely lightweight neural network trained on monocular video sequences for real-time unsupervised monocular depth estimation, which opens up the possibility of implementing deep learning-based real-time unsupervised monocular depth prediction on low-cost embedded devices. Copyright © 2020, The Authors. All rights reserved.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Learning to predict context-adaptive convolution for semantic segmentation

arXiv

引用

arXiv 2020年

作者： Liu, Jianbo He, Junjun Ren, Jimmy S. Qiao, Yu Li, Hongsheng CUHK-SenseTime Joint Laboratory Chinese University of Hong Kong Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SenseTime Research

Long-range contextual information is essential for achieving high-performance semantic segmentation. Previous feature re-weighting methods [34] demonstrate that using global context for re-weighting feature channels can effectively improve the accuracy of semantic segmentation. However, the globally-sharing feature re-weighting vector might not be optimal for regions of different classes in the input image. In this paper, we propose a Context-adaptive Convolution Network (CaC-Net) to predict a spatially-varying feature weighting vector for each spatial location of the semantic feature maps. In CaC-Net, a set of context-adaptive convolution kernels are predicted from the global contextual information in a parameter-efficient manner. When used for convolution with the semantic feature maps, the predicted convolutional kernels can generate the spatially-varying feature weighting factors capturing both global and local contextual information. Comprehensive experimental results show that our CaC-Net achieves superior segmentation performance on three public datasets, PASCAL Context, PASCAL VOC 2012 and ADE20K. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Context-transformer: Tackling object confusion for few-shot detection

arXiv

引用

arXiv 2020年

作者： Yang, Ze Wang, Yali Chen, Xianyu Liu, Jianzhuang Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab. Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Huawei Noah’s Ark Lab. SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

Few-shot object detection is a challenging but realistic scenario, where only a few annotated training images are available for training detectors. A popular approach to handle this problem is transfer learning, i.e., fine-tuning a detector pretrained on a source-domain benchmark. However, such transferred detector often fails to recognize new objects in the target domain, due to low data diversity of training samples. To tackle this problem, we propose a novel Context-Transformer within a concise deep transfer framework. Specifically, Context-Transformer can effectively leverage source-domain object knowledge as guidance, and automatically exploit contexts from only a few training images in the target domain. Subsequently, it can adaptively integrate these relational clues to enhance the discriminative power of detector, in order to reduce object confusion in few-shot scenarios. Moreover, Context-Transformer is flexibly embedded in the popular SSD-style detectors, which makes it a plug-and-play module for end-to-end few-shot learning. Finally, we evaluate Context-Transformer on the challenging settings of few-shot detection and incremental few-shot detection. The experimental results show that, our framework outperforms the recent state-of-the-art approaches. The codes are available at https://***/Ze-Yang/ContextTransformer. Copyright © 2020, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report

Power Efficient Video Super-Resolution on Mobile NPUs with...

引用

17th European Conference on computer vision, ECCV 2022

作者： Ignatov, Andrey Timofte, Radu Chiang, Cheng-Ming Kuo, Hsien-Kai Xu, Yu-Syuan Lee, Man-Yu Lu, Allen Cheng, Chia-Ming Chen, Chih-Cheng Yong, Jia-Ying Shuai, Hong-Han Cheng, Wen-Huang Jia, Zhuang Xu, Tianyu Zhang, Yijian Bao, Long Sun, Heng Zhang, Diankai Gao, Si Liu, Shaoli Wu, Biao Zhang, Xiaofeng Zheng, Chengjian Lu, Kaidi Wang, Ning Sun, Xiao Wu, HaoDong Liu, Xuncheng Zhang, Weizhan Yan, Caixia Du, Haipeng Zheng, Qinghua Wang, Qi Chen, Wangdu Duan, Ran Sun, Mengdi Zhu, Dan Chen, Guannan Cho, Hojin Kim, Steve Yue, Shijie Li, Chenghua Zhuge, Zhengyang Chen, Wei Wang, Wenxu Zhou, Yufeng Cai, Xiaochen Cai, Hengxing Xu, Kele Liu, Li Cheng, Zehua Lian, Wenyi Lian, Wenjing Computer Vision Lab ETH Zurich Zürich Switzerland AI Witchlabs Zürich Switzerland University of Wuerzburg Würzburg Germany MediaTek Inc. Hsinchu Taiwan National Yang Ming Chiao Tung University Hsinchu Taiwan Video Algorithm Group Camera Department Xiaomi Inc. Beijing China Audio & Video Technology Platform Department ZTE Corporation Shenzhen China Beijing China School of Computer Science and Technology Xi’an Jiaotong University Xi’an China MIGU Video Co. Ltd. Beijing China BOE Technology Group Co. Ltd. Beijing China GenGenAI Seoul Korea Republic of North China University of Technology Beijing China Institute of Automation Chinese Academy of Sciences Beijing China State Key Laboratory of Computer Architecture Institute of Computing Technology Beijing China 4Paradigm Inc. Beijing China National University of Defense Technology Changsha China University of Oxford Oxford United Kingdom Uppsala University Uppsala Sweden Northeastern University Shenyang China

ISBN: (纸本)9783031250651

Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of low-bitrate and low-resolution video streams. While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices. In this Mobile AI challenge, we address this problem and propose the participants to design an end-to-end real-time video super-resolution solution for mobile NPUs optimized for low energy consumption. The participants were provided with the REDS training dataset containing video sequences for a 4X video upscaling task. The runtime and power efficiency of all models was evaluated on the powerful MediaTek Dimensity 9000 platform with a dedicated AI processing unit capable of accelerating floating-point and quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 500 FPS rate and 0.2 [Watt/30 FPS] power consumption. A detailed description of all models developed in the challenge is provided in this paper. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Assessing performance of augmented reality-based neurosurgical training

引用

Visual Computing for Industry,Biomedicine,and Art 2019年第1期2卷 45-54页

作者： Wei-Xin Si Xiang-Yun Liao Yin-Ling Qian Hai-Tao Sun Xiang-Dong Chen Qiong Wang Pheng Ann Heng Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced TechnologyChinese Academy of Sciences1068 Xueyuan AvenueShenzhen University TownShenzhen 518055China Department of Neurosurgery Zhujiang HospitalSouthern Medical UniversityGuangzhou 510282China E.N.T.department of Shenzhen University General Hospital Shenzhen 518055China Department of Computer Science and Engineering the Chinese University of Hong KongHong KongChina

This paper presents a novel augmented reality(AR)-based neurosurgical training simulator which provides a very natural way for surgeons to learn neurosurgical *** simulation with bimanual haptic interaction is integrated in this work to provide a simulated environment for users to achieve holographic guidance for pre-operative *** achieve the AR guidance,the simulator should precisely overlay the 3D anatomical information of the hidden target organs in the patients in real *** this regard,the patient-specific anatomy structures are reconstructed from segmented brain magnetic resonance *** propose a registration method for precise mapping of the virtual and real *** addition,the simulator provides bimanual haptic interaction in a holographic environment to mimic real brain tumor *** this study,we conduct AR-based guidance validation and a user study on the developed simulator,which demonstrate the high accuracy of our AR-based neurosurgery simulator,as well as the AR guidance mode’s potential to improve neurosurgery by simplifying the operation,reducing the difficulty of the operation,shortening the operation time,and increasing the precision of the operation.

关键词： Augmented reality Personalized virtual operative anatomy Neurosurgical training

来源：评论

学校读者我要写书评

暂无评论

Tumor Detection, Segmentation and Classification Challenge on Automated 3D Breast Ultrasound: The TDSC-ABUS Challenge

arXiv

引用

arXiv 2025年

作者： Luo, Gongning Xu, Mingwang Chen, Hongyu Liang, Xinjie Tao, Xing Ni, Dong Jeong, Hyunsu Kim, Chulhong Stock, Raphael Baumgartner, Michael Kirchhoff, Yannick Rokuss, Maximilian Maier-Hein, Klaus Yang, Zhikai Fan, Tianyu Boutry, Nicolas Tereshchenko, Dmitry Moine, Arthur Charmetant, Maximilien Sauer, Jan Du, Hao Bai, Xiang-Hui Raikar, Vipul Pai Montoya-Del-Angel, Ricardo Martí, Robert Luna, Miguel Lee, Dongmin Qayyum, Abdul Mazher, Moona Guo, Qihui Wang, Changyan Awasthi, Navchetan Zhao, Qiaochu Wang, Wei Wang, Kuanquan Wang, Qiucheng Dong, Suyu School of Computer Science and Technology Harbin Institute of Technology Harbin150001 China Department of Mathematics Faculty of Science National University of Singapore Singapore National-Regional Key Technology Engineering Laboratory for Medical Ultrasound School of Biomedical Engineering Shenzhen University Medical School Shenzhen University Shenzhen China Laboratory Shenzhen University Shenzhen China School of Biomedical Engineering and Informatics Nanjing Medical University Nanjing China Pohang Korea Republic of Heidelberg Division of Medical Image Computing Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Germany Heidelberg Germany HIDSS4Health - Helmholtz Information and Data Science School for Health Karlsruhe Heidelberg Germany Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Germany Department of Biomedical Engineering and Health KTH Royal Institute of Technology Stockholm Sweden France FathomX Singapore Saw Swee Hock School of Public Health National University of Singapore Singapore Philips Research University of Girona Spain Department of Robotics and Mechatronics Engineering DGIST Korea Republic of Department of Interdisciplinary Studies of Artificial Intelligence DGIST Korea Republic of National Heart and Lung Institute Faculty of Medicine Imperial College London London United Kingdom Centre for Medical Image Computing Department of Computer Science University College London London United Kingdom Lab School of Communication and Information Engineering Shanghai University Shanghai China Faculty of Science Mathematics and Computer Science Informatics Institute University of Amsterdam Amsterdam1090 GH Netherlands Department of Biomedical Engineering and Physics Amsterdam UMC Amsterdam1081 HV Netherlands Xi’an Jiaotong-Liverpool University China Department of Ultrasound Harbin Medical University Cancer Hospital No. 150 Haping Road Nangang

Breast cancer is one of the most common causes of death among women worldwide. Early detection helps in reducing the number of deaths. Automated 3D Breast Ultrasound (ABUS) is a newer approach for breast screening, which has many advantages over handheld mammography such as safety, speed, and higher detection rate of breast cancer. Tumor detection, segmentation, and classification are key components in the analysis of medical images, especially challenging in the context of 3D ABUS due to the significant variability in tumor size and shape, unclear tumor boundaries, and a low signal-to-noise ratio. The lack of publicly accessible, well-labeled ABUS datasets further hinders the advancement of systems for breast tumor analysis. Addressing this gap, we have organized the inaugural Tumor Detection, Segmentation, and Classification Challenge on Automated 3D Breast Ultrasound 2023 (TDSC-ABUS2023). This initiative aims to spearhead research in this field and create a definitive benchmark for tasks associated with 3D ABUS image analysis. In this paper, we summarize the top-performing algorithms from the challenge and provide critical analysis for ABUS image examination. We offer the TDSC-ABUS challenge as an open-access platform at https://***/ to benchmark and inspire future developments in1algorithmic research. © 2025, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Conditional sequential modulation for efficient global image retouching

arXiv

引用

arXiv 2020年

作者： He, Jingwen Liu, Yihao Qiao, Yu Dong, Chao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China SIAT Branch Shenzhen Institute of Artificial Intelligence Robotics for Society Korea Republic of University of Chinese Academy of Sciences China

Photo retouching aims at enhancing the aesthetic visual quality of images that suffer from photographic defects such as over/under exposure, poor contrast, inharmonious saturation. Practically, photo retouching can be accomplished by a series of image processing operations. In this paper, we investigate some commonly-used retouching operations and mathematically find that these pixel-independent operations can be approximated or formulated by multi-layer perceptrons (MLPs). Based on this analysis, we propose an extremely light-weight framework - Conditional Sequential Retouching Network (CSRNet) - for efficient global image retouching. CSRNet consists of a base network and a condition network. The base network acts like an MLP that processes each pixel independently and the condition network extracts the global features of the input image to generate a condition vector. To realize retouching operations, we modulate the intermediate features using Global Feature Modulation (GFM), of which the parameters are transformed by condition vector. Benefiting from the utilization of 1×1 convolution, CSRNet only contains less than 37k trainable parameters, which is orders of magnitude smaller than existing learning-based methods. Extensive experiments show that our method achieves state-of-the-art performance on the benchmark MIT-Adobe FiveK dataset quantitively and qualitatively. Code is available at https://***/hejingwenhejingwen/CSRNet. Copyright © 2020, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Deep Semi-supervised Knowledge Distillation for Overlapping Cervical Cell Instance Segmentation

arXiv

引用

arXiv 2020年

作者： Zhou, Yanning Chen, Hao Lin, Huangjing Heng, Pheng-Ann Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong Hong Kong Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

Deep learning methods show promising results for overlapping cervical cell instance segmentation. However, in order to train a model with good generalization ability, voluminous pixel-level annotations are demanded which is quite expensive and time-consuming for acquisition. In this paper, we propose to leverage both labeled and unlabeled data for instance segmentation with improved accuracy by knowledge distillation. We propose a novel Mask-guided Mean Teacher framework with Perturbation-sensitive Sample Mining (MMT-PSM), which consists of a teacher and a student network during training. Two networks are encouraged to be consistent both in feature and semantic level under small perturbations. The teacher’s self-ensemble predictions from K-time augmented samples are used to construct the reliable pseudo-labels for optimizing the student. We design a novel strategy to estimate the sensitivity to perturbations for each proposal and select informative samples from massive cases to facilitate fast and effective semantic distillation. In addition, to eliminate the unavoidable noise from the background region, we propose to use the predicted segmentation mask as guidance to enforce the feature distillation in the foreground region. Experiments show that the proposed method improves the performance significantly compared with the supervised method learned from labeled data only, and outperforms state-of-the-art semi-supervised methods. Code: https://***/SIAAAAAA/MMT-PSM. Copyright © 2020, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization

arXiv

引用

arXiv 2020年

作者： Wang, Shujun Li, Caizi Heng, Pheng-Ann Fu, Chi-Wing Yu, Lequan Chinese University of Hong Kong Hong Kong Stanford University Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

The generalization capability of neural networks across domains is crucial for real-world applications. We argue that a generalized object recognition system should well understand the relationships among different images and also the images themselves at the same time. To this end, we present a new domain generalization framework (called EISNet) that learns how to generalize across domains simultaneously from extrinsic relationship supervision and intrinsic self-supervision for images from multi-source domains. To be specific, we formulate our framework with feature embedding using a multi-task learning paradigm. Besides conducting the common supervised recognition task, we seamlessly integrate a momentum metric learning task and a self-supervised auxiliary task to collectively integrate the extrinsic and intrinsic supervisions. Also, we develop an effective momentum metric learning scheme with the K-hard negative mining to boost the network generalization ability. We demonstrate the effectiveness of our approach on two standard object recognition benchmarks VLCS and PACS, and show that our EISNet achieves state-of-the-art performance. Copyright © 2020, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration

arXiv

引用

arXiv 2020年

作者： Gu, Jinjin Cai, Haoming Chen, Haoyu Ye, Xiaoxing Ren, Jimmy S. Dong, Chao School of Data Science Chinese University of Hong Kong Shenzhen China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China SenseTime Research SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Image quality assessment (IQA) is the key factor for the fast development of image restoration (IR) algorithms. The most recent IR methods based on Generative Adversarial Networks (GANs) have achieved significant improvement in visual performance, but also presented great challenges for quantitative evaluation. Notably, we observe an increasing inconsistency between perceptual quality and the evaluation results. Then we raise two questions: (1) Can existing IQA methods objectively evaluate recent IR algorithms? (2) When focus on beating current benchmarks, are we getting better IR algorithms? To answer these questions and promote the development of IQA methods, we contribute a large-scale IQA dataset, called Perceptual Image Processing Algorithms (PIPAL) dataset. Especially, this dataset includes the results of GAN-based methods, which are missing in previous datasets. We collect more than 1.13 million human judgments to assign subjective scores for PIPAL images using the more reliable "Elo system". Based on PIPAL, we present new benchmarks for both IQA and super-resolution methods. Our results indicate that existing IQA methods cannot fairly evaluate GAN-based IR algorithms. While using appropriate evaluation methods is important, IQA methods should also be updated along with the development of IR algorithms. At last, we improve the performance of IQA networks on GAN-based distortions by introducing anti-aliasing pooling. Experiments show the effectiveness of the proposed method. Copyright © 2020, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：