检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Dong, Jiahua Li, Hongliu Cong, Yang Sun, Gan Zhang, Yulun Van Gool, Luc The State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China The Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China The University of Chinese Academy of Sciences Beijing100049 China The Department of Civil and Environmental Engineering Hong Kong Polytechnic University Hong Kong The College of Automation Science and Engineering South China University of Technology Guangzhou510640 China The Computer Vision Lab ETH Zürich Zürich8092 Switzerland

Federated learning (FL) is a hot collaborative training framework via aggregating model parameters of decentralized local clients. However, most FL methods unreasonably assume data categories of FL framework are known and fixed in advance. Moreover, some new local clients that collect novel categories unseen by other clients may be introduced to FL training irregularly. These issues render global model to undergo catastrophic forgetting on old categories, when local clients receive new categories consecutively under limited memory of storing old categories. To tackle the above issues, we propose a novel Local-Global Anti-forgetting (LGA) model. It ensures no local clients are left behind as they learn new classes continually, by addressing local and global catastrophic forgetting. Specifically, considering tackling class imbalance of local client to surmount local forgetting, we develop a category-balanced gradient-adaptive compensation loss and a category gradient-induced semantic distillation loss. They can balance heterogeneous forgetting speeds of hard-to-forget and easy-to-forget old categories, while ensure consistent class-relations within different tasks. Moreover, a proxy server is designed to tackle global forgetting caused by Non-IID class imbalance between different clients. It augments perturbed prototype images of new categories collected from local clients via self-supervised prototype augmentation, thus improving robustness to choose the best old global model for local-side semantic distillation loss. Experiments on representative datasets verify superior performance of our model against comparison methods. The code is available at https://***/JiahuaDong/LGA. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Neural Gradient Regularizer

arXiv

引用

arXiv 2023年

作者： Xu, Shuang Wang, Yifan Zhao, Zixiang Peng, Jiangjun Cao, Xiangyong Meng, Deyu Zhang, Yulun Timofte, Radu Van Gool, Luc School of Mathematics and Statistics Northwestern Polytechnical University Xi’an710021 China Research and Development Institute Northwestern Polytechnical University in Shenzhen Shenzhen518063 China School of Electronic and Information Engineering The Key Laboratory for Intelligent Networks and Network Security Ministry of Education Xi’an Jiaotong University Xi’an710049 China School of Mathematics and Statistics Xi’an Jiaotong University Xi’an710049 China Computer Vision Lab ETH Zurich Zürich8092 Switzerland

Owing to its significant success, the prior imposed on gradient maps has consistently been a subject of great interest in the field of image processing. Total variation (TV), one of the most representative regularizers, is known for its ability to capture the intrinsic sparsity prior underlying gradient maps. Nonetheless, TV and its variants often underestimate the gradient maps, leading to the weakening of edges and details whose gradients should not be zero in the original image (i.e., image structures is not describable by sparse priors of gradient maps). Recently, total deep variation (TDV) has been introduced, assuming the sparsity of feature maps, which provides a flexible regularization learned from large-scale datasets for a specific task. However, TDV requires to retrain the network with image/task variations, limiting its versatility. To alleviate this issue, in this paper, we propose a neural gradient regularizer (NGR) that expresses the gradient map as the output of a neural network. Unlike existing methods, NGR does not rely on any subjective sparsity or other prior assumptions on image gradient maps, thereby avoiding the underestimation of gradient maps. NGR is applicable to various image types and different image processing tasks, functioning in a zero-shot learning fashion, making it a versatile and plug-and-play regularizer. Extensive experimental results demonstrate the superior performance of NGR over state-of-the-art counterparts for a range of different tasks, further validating its effectiveness and versatility. © 2023, CC BY.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Investigate indistinguishable points in semantic segmentation of 3D point cloud

arXiv

引用

arXiv 2021年

作者： Xu, Mingye Zhou, Zhipeng Zhang, Junhao Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences China Shanghai AI Lab Shanghai China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

This paper investigates the indistinguishable points (difficult to predict label) in semantic segmentation for large-scale 3D point clouds. The indistinguishable points consist of those located in complex boundary, points with similar local textures but different categories, and points in isolate small hard areas, which largely harm the performance of 3D semantic segmentation. To address this challenge, we propose a novel Indistinguishable Area Focalization Network (IAF-Net), which selects indistinguishable points adaptively by utilizing the hierarchical semantic features and enhance fine-grained features for points especially those indistinguishable points. We also introduce multi-stage loss to improve the feature representation in a progressive way. Moreover, in order to analyze the segmentation performances of indistinguishable areas, we propose a new evaluation metric called Indistinguishable Points Based Metric (IPBM). Our IAF-Net achieves the comparable results with state-of-the-art performance on several popular 3D point cloud datasets e.g. S3DIS and ScanNet, and clearly outperforms other methods on IPBM. Our code will be available at https://***/MingyeXu/IAF-Net. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantic Segmentation

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 1

引用

16th European Conference on computer vision, ECCV 2020

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

ISBN: (数字)9783030585457

ISBN: (纸本)9783030585440

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. © 2020, Springer Nature Switzerland AG.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

EfficientFCN: Holistically-Guided Decoding for Semantic Segmentation 1

引用

16th European Conference on computer vision, ECCV 2020

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

ISBN: (数字)9783030585747

ISBN: (纸本)9783030585730

Both performance and efficiency are important to semantic segmentation. State-of-the-art semantic segmentation algorithms are mostly based on dilated Fully Convolutional Networks (dilatedFCN), which adopt dilated convolutions in the backbone networks to extract high-resolution feature maps for achieving high-performance segmentation performance. However, due to many convolution operations are conducted on the high-resolution feature maps, such dilatedFCN-based methods result in large computational complexity and memory consumption. To balance the performance and efficiency, there also exist encoder-decoder structures that gradually recover the spatial information by combining multi-level feature maps from the encoder. However, the performances of existing encoder-decoder methods are far from comparable with the dilatedFCN-based methods. In this paper, we propose the EfficientFCN, whose backbone is a common ImageNet pretrained network without any dilated convolution. A holistically-guided decoder is introduced to obtain the high-resolution semantic-rich feature maps via the multi-scale features from the encoder. The decoding task is converted to novel codebook generation and codeword assembly task, which takes advantages of the high-level and low-level features from the encoder. Such a framework achieves comparable or even better performance than state-of-the-art methods with only 1/3 of the computational cost. Extensive experiments on PASCAL Context, PASCAL VOC, ADE20K validate the effectiveness of the proposed EfficientFCN. © 2020, Springer Nature Switzerland AG.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

An Improved SSD for small target detection

An Improved SSD for small target detection

引用

作者： Xiang Li Haibo LuoX Key Laboratory of Opt-Electronic Information Processing Chinese Academy of Sciences Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences University of Chinese Academy of Sciences The Key Laboratory of Image Understanding and Computer Vision

SSD is one of heuristic one-stage target detection *** it has got impressive results in general target detection,it still struggles in small-size object detection and precise *** this paper,we proposed an improved SSD which forces on the small-size target *** include a shallow and high resolution feature into the hierarchical detection feature which are used for ***,we fuse the detection features(including the shallow and high resolution one) as a feature pyramid through some 1 × 1 convolution layers and unsample operations to pass information from deep features to the shallow ones,aiming to enrich the semantic information of the shallow *** make the network easier to converge,we add a L2 normalization to the bottom detection feature of the feature pyramid to make a norm balance between each pyramid *** experimental results on the VEDAI dataset show that the proposed method has obtained impressive progress than the original SSD for the small targets detection.

关键词： Convolution neural network Target detection SSD Small targets

来源：评论

学校读者我要写书评

暂无评论

Tactile-Based Object Pose Estimation Employing Extended Kalman Filter

Tactile-Based Object Pose Estimation Employing Extended Kalm...

引用

International Conference on Advanced robotics and Mechatronics (ICARM)

作者： Qiguang Lin Chaojie Yan Qiang Li Yonggen Ling Yu Zheng Wangwei Lee Zhaoliang Wan Bidan Huang Xiaofeng Liu Jiangsu Key laboratory of Special Robotic Technology College of IoT Engineering Hohai University Changzhou Jiangsu P.R. China State Key Laboratory of Industrial Control and Technology Zhejiang University Institute of Cyber-System and Control Hangzhou P.R. China Neuroinformatics Group Center for Cognitive Interaction Technology (CITEC) Bielefeld University Bielefeld Germany Tencent Robotics X Shenzhen China School of Computer Science and Engineering Sun Yat-sen University Guangzhou P.R.China

In this paper, we present a new approach to estimate the pose of an object being manipulated by a multi-fingered robotic hand. The method utilizes advanced tactile sensors with high spatial resolution to optimize the estimation of the object's pose using an Extended Kalman Filter (EKF) based approach. We defined and derived the state and measurement equations, as well as evaluated the estimation accuracy in grasping tasks. The approach is able to effectively account for the pose transition caused by tactile pushing, and the mapping from the object's pose to the contact position and normal direction as measured by the tactile sensor. The method was evaluated in multiple grasping experiments in simulation scenarios. Results show that the estimation can converge towards the ground truth in a relatively short period of time, with displacement and rotation errors remaining within acceptable levels. This new method has the potential to improve the accuracy and reliability of robotic grasping and manipulation tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

G-MAP: General Memory-Augmented Pre-trained Language Model for Domain Tasks

arXiv

引用

arXiv 2022年

作者： Wan, Zhongwei Yin, Yichun Zhang, Wei Shi, Jiaxin Shang, Lifeng Chen, Guangyong Jiang, Xin Liu, Qun Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Science China University of Chinese Academy of Sciences China Huawei Noah's Ark Lab Hong Kong Huawei Cloud Computing Zhejiang Lab China

Recently, domain-specific PLMs have been proposed to boost the task performance of specific domains (e.g., biomedical and computer science) by continuing to pre-train general PLMs with domain-specific corpora. However, this Domain-Adaptive Pre-Training (DAPT;Gururangan et al. (2020)) tends to forget the previous general knowledge acquired by general PLMs, which leads to a catastrophic forgetting phenomenon and sub-optimal performance. To alleviate this problem, we propose a new framework of General Memory- Augmented Pre-trained Language Model (GMAP), which augments the domain-specific PLM by a memory representation built from the frozen general PLM without losing any general knowledge. Specifically, we propose a new memory-augmented layer, and based on it, different augmented strategies are explored to build the memory representation and then adaptively fuse it into the domain-specific PLM. We demonstrate the effectiveness of G-MAP on various domains (biomedical and computer science publications, news, and reviews) and different kinds (text classification, QA, NER) of tasks, and the extensive results show that the proposed G-MAP1 can achieve SOTA results on all tasks. © 2022, CC BY.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Super-resolving Compressed Images via Parallel and Series Integration of Artifact Reduction and Resolution Enhancement

arXiv

引用

arXiv 2021年

作者： Luo, Hongming Zhou, Fei Liao, Guangsen Qiu, Guoping College of Electronics and Information Engineering Shenzhen University China Peng Cheng Laboratory Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen Key Laboratory of Digital Creative Technology China Shenzhen Institute for Artificial Intelligence and Robotics for Society Shenzhen China School of Computer Science University of Nottingham NottinghamNG8 1BB United Kingdom Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication Guangdong Shenzhen China

In real-world applications, such as sharing photos on social media platforms, images are always not only sub-sampled but also heavily compressed thus often containing various artefacts. Simple methods for enhancing the resolution of such images will exacerbate the artefacts, rendering them visually objectionable. In spite of its high practical values, super-resolving compressed images is not well studied in the literature. In this paper, we propose a novel compressed image super resolution (CISR) framework based on parallel and series integration of artefacts removal and resolution enhancement. Based on a mathematical inference model for estimating a clean low-resolution (LR) image and a clean high-resolution (HR) image from a down-sampled and compressed observation, we have designed a CISR architecture consisting of two deep neural network modules: the artefacts removal module (ARM) and the resolution enhancement module (REM). The ARM and the REM work in parallel with both taking the compressed LR image as their inputs, at the same time they also work in series with the REM taking the output of the ARM as one of its inputs and the ARM taking the output of the REM as its other input. A technique called unfolding is introduced to recursively suppress the compression artefacts and restore the image resolution. A unique feature of our CISR system is that it exploits the parallel and series connections between the ARM and the REM, and recursive optimization to reduce the model's dependency on specific types of degradation thus making it possible to train a single model to super-resolve images compressed by different methods to different qualities. Experiments are conducted on a mixture of JPEG and WebP compressed images without assuming apriori compression type and compression quality factor. To demonstrate our technique's real-world application value, we have also applied the trained models directly to restore social media images which have undergone scaling and compre

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Dual-teacher: Integrating intra-domain and inter-domain teachers for annotation-efficient cardiac segmentation 23rd

Dual-teacher: Integrating intra-domain and inter-domain teac...

引用

23rd International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2020

作者： Li, Kang Wang, Shujun Yu, Lequan Heng, Pheng-Ann Department of Computer Science and Engineering The Chinese University of Hong Kong Shatin Hong Kong Department of Radiation Oncology Stanford University Stanford United States Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (纸本)9783030597092

Medical image annotations are prohibitively time-consuming and expensive to obtain. To alleviate annotation scarcity, many approaches have been developed to efficiently utilize extra information, e.g., semi-supervised learning further exploring plentiful unlabeled data, domain adaptation including multi-modality learning and unsupervised domain adaptation resorting to the prior knowledge from additional modality. In this paper, we aim to investigate the feasibility of simultaneously leveraging abundant unlabeled data and well-established cross-modality data for annotation-efficient medical image segmentation. To this end, we propose a novel semi-supervised domain adaptation approach, namely Dual-Teacher, where the student model not only learns from labeled target data (e.g., CT), but also explores unlabeled target data and labeled source data (e.g., MR) by two teacher models. Specifically, the student model learns the knowledge of unlabeled target data from intra-domain teacher by encouraging prediction consistency, as well as the shape priors embedded in labeled source data from inter-domain teacher via knowledge distillation. Consequently, the student model can effectively exploit the information from all three data resources and comprehensively integrate them to achieve improved performance. We conduct extensive experiments on MM-WHS 2017 dataset and demonstrate that our approach is able to concurrently utilize unlabeled data and cross-modality data with superior performance, outperforming semi-supervised learning and domain adaptation methods with a large margin. © Springer Nature Switzerland AG 2020.

关键词： Distillation

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：