检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wang, Yuxi Liang, Jian Xiao, Jun Mei, Shuqi Yang, Yuran Zhang, Zhaoxiang Centre for Artificial Intelligence and Robotics HKISI-CAS Hong Kong Institute of Automation Chinese Academy of Sciences China University of Chinese Academy of Sciences China State Key Laboratory of Multimodal Artificial Intelligence Systems China Tencent China

Contemporary domain adaptation offers a practical solution for achieving cross-domain transfer of semantic segmentation between labelled source data and unlabeled target data. These solutions have gained significant popularity;however, they require the model to be retrained when the test environment changes. This can result in unbearable costs in certain applications due to the time-consuming training process and concerns regarding data privacy. One-shot domain adaptation methods attempt to overcome these challenges by transferring the pre-trained source model to the target domain using only one target data. Despite this, the referring style transfer module still faces issues with computation cost and over-fitting problems. To address this problem, we propose a novel framework called Informative Data Mining (IDM) that enables efficient one-shot domain adaptation for semantic segmentation. Specifically, IDM provides an uncertainty-based selection criterion to identify the most informative samples, which facilitates quick adaptation and reduces redundant training. We then perform a model adaptation method using these selected samples, which includes patch-wise mixing and prototype-based information maximization to update the model. This approach effectively enhances adaptation and mitigates the overfitting problem. In general, we provide empirical evidence of the effectiveness and efficiency of IDM. Our approach outperforms existing methods and achieves a new state-of-the-art one-shot performance of 56.7%/55.4% on the GTA5/SYNTHIA to Cityscapes adaptation tasks, respectively. The code will be released at https://***/yxiwang/IDM. Copyright © 2023, The Authors. All rights reserved.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

A Terrain Segmentation Method Based on U-MobileNet for Navigation of Outdoor Robots

A Terrain Segmentation Method Based on U-MobileNet for Navig...

引用

第34届中国控制与决策会议

作者： Tao Hong Botao Zhang Qi'an Zhang Sergey A.Chepinskiy Anton A.Zhilenkov School of Automation Hangzhou Dianzi University Faculty of Control Systems and Robotics ITMO University Institute of Hydrodynamics and Control Processes Saint-Petersburg State Marine Technical University

Terrain segmentation is widely used in the recognition and navigation of outdoor mobile robots,in which deep learning-based segmentation methods have achieved remarkable ***,most of the segmentation networks can hardly meet the real-time requirement for outdoor robots.A novel terrain segmentation approach is proposed for segmentation terrains in the navigation of robots based on U-MobileNet.U-MobileNet,a lightweight segmentation network,is formed by transposing the feature extraction structure of MobileNetV2 to the contracting path of *** network efficiently reduce the computational cost and the error in segmentation by applying depth wise separable convolution,inverted residual and linear *** experimental results show that the proposed lightweight neural network has good real-time performance with high-accuracy.

关键词： Mobile robot Navigation Terrain segmentation Visual perception Inverted residual

来源：评论

学校读者我要写书评

暂无评论

A modified YOLOv4 detection method for a vision-based underwater garbage cleaning robot

引用

Frontiers of Information Technology & Electronic Engineering 2022年第8期23卷 1217-1228页

作者： Manjun TIAN Xiali LI Shihan KONG Licheng WU Junzhi YU First Research Institute of the Ministry of Public Security of PRC Beijing 100048China School of Information Engineering Minzu University of ChinaBeijing 100081China Department of Advanced Manufacturing and Robotics College of EngineeringPeking UniversityBeijing 100871China State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

To tackle the problem of aquatic environment pollution,a vision-based autonomous underwater garbage cleaning robot has been developed in our *** propose a garbage detection method based on a modified YOLOv4,allowing high-speed and high-precision object ***,the YOLOv4 algorithm is chosen as a basic neural network framework to perform object *** the purpose of further improvement on the detection accuracy,YOLOv4 is transformed into a four-scale detection *** improve the detection speed,model pruning is applied to the new *** virtue of the improved detection methods,the robot can collect garbage *** detection speed is up to 66.67 frames/s with a mean average precision(mAP)of 95.099%,and experimental results demonstrate that both the detection speed and the accuracy of the improved YOLOv4 are excellent.

关键词： Object detection Aquatic environment Garbage cleaning robot Modified YOLOv4

来源：评论

学校读者我要写书评

暂无评论

Robotic Single-Micropipette Enucleation Method for Zona-free Oocytes

Robotic Single-Micropipette Enucleation Method for Zona-free...

引用

Chinese Control Conference (CCC)

作者： Yidi Zhang Yaowei Liu Minghui Li Dong Sun Xin Zhao Institute of Robotics and Automatic Information System (IRAIS) and the Tianjin Key Laboratory of Intelligent Robotic (tjKLIR) Nankai University Tianjin China Department of Biomedical Engineering City University of Hong Kong Hong Kong SAR China Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University Shenzhen China Centre for Robotics and Automation Shenzhen Research Institute City University of Hong Kong Shenzhen China

Somatic cell nuclear transfer is a mammalian cloning method that involves replacing the oocyte nucleus with a somatic cell nucleus. One of the most critical steps in this process is the efficient production of large numbers of enucleated oocytes. While a single-micropipette-based manual enucleation method has been widely used in manual cloning, it is still a manual operation that requires exceptional technical skills and experience. Additionally, it is difficult to accurately control the amount of enucleation and to meet the demand for high-throughput enucleation. Therefore, we propose a robotic enucleation method using a single micropipette for zona-free oocytes, which allows for the detection and control of the amount of enucleation, as well as continuous enucleation on a large scale. A single oocyte enucleation can be completed in less than 13 seconds. This robotic enucleation method provides a solution for enhancing the operational efficiency of robotic somatic cell nuclear transfer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Practical Continual Forgetting for Pre-trained Vision Models

arXiv

引用

arXiv 2025年

作者： Zhao, Hongbo Zhu, Fei Ni, Bolin Zhu, Feng Meng, Gaofeng Zhang, Zhaoxiang State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100190 China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences 999077 Hong Kong SenseTime Research Beijing100084 China

For privacy and security concerns, the need to erase unwanted information from pre-trained vision models is becoming evident nowadays. In real-world scenarios, erasure requests originate at any time from both users and model owners, and these requests usually form a sequence. Therefore, under such a setting, selective information is expected to be continuously removed from a pre-trained model while maintaining the rest. We define this problem as continual forgetting and identify three key challenges. (i) For unwanted knowledge, efficient and effective deleting is crucial. (ii) For remaining knowledge, the impact brought by the forgetting procedure should be minimal. (iii) In real-world scenarios, the training samples may be scarce or partially missing during the process of forgetting. To address them, we first propose Group Sparse LoRA (GS-LoRA). Specifically, towards (i), we introduce LoRA modules to fine-tune the FFN layers in Transformer blocks for each forgetting task independently, and towards (ii), a simple group sparse regularization is adopted, enabling automatic selection of specific LoRA groups and zeroing out the others. To further extend GS-LoRA to more practical scenarios, we incorporate prototype information as additional supervision and introduce a more practical approach, GS-LoRA++. For each forgotten class, we move the logits away from its original prototype. For the remaining classes, we pull the logits closer to their respective prototypes. We conduct extensive experiments on face recognition, object detection and image classification and demonstrate that our method manages to forget specific classes with minimal impact on other classes. Codes have been released on https://***/bjzhb666/GS-LoRA. Copyright © 2025, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Novel Dynamically Differentiated Access Scheme for Massive Grant-Free NOMA

A Novel Dynamically Differentiated Access Scheme for Massive...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Yitian Wang Meng Zheng Haibin Yu Wei Liang State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Shenyang China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665454698

Facing the dual challenges of massive access and time-sensitive traffics, grant-free non-orthogonal multiple access (GF-NOMA) emerges as a promising technology for implementing massive ultra-reliable and low-latency communications (mURLLC). In this paper, we propose a differentiated power level access (DPLA) policy that exploits the correlations among power levels of GF-NOMA, and implement DPLA by a dynamically distributed GF-NOMA framework. Further, a closed-form expression to the reliability of DPLA is analytically derived and the optimal framework parameters to maximize reliability are obtained. Finally, considering the traffic variation over time, we propose a dynamically-distributed differentiated-layered transmission $(\mathrm{D}^{3}$ LT) algorithm to improve the reliability online. Simulation results show that the proposed scheme in this work outweighs existing schemes in transmission reliability.

关键词： NOMA Vehicular and wireless technologies Correlation Closed-form solutions Simulation Heuristic algorithms Reliability

来源：评论

学校读者我要写书评

暂无评论

DropPos: pre-training vision transformers by reconstructing dropped positions 23

DropPos: pre-training vision transformers by reconstructing ...

引用

Proceedings of the 37th International Conference on Neural Information Processing systems

作者： Haochen Wang Junsong Fan Yuxi Wang Kaiyou Song Tong Wang Zhaoxiang Zhang Center for Research on Intelligent Perception and Computing (CRIPAC) State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) Institute of Automation Chinese Academy of Sciences (CASIA) and University of Chinese Academy of Sciences (UCAS) Center for Research on Intelligent Perception and Computing (CRIPAC) State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) Institute of Automation Chinese Academy of Sciences (CASIA) and Centre for Artificial Intelligence and Robotics HKISI_CAS Megvii Technology Center for Research on Intelligent Perception and Computing (CRIPAC) State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) Institute of Automation Chinese Academy of Sciences (CASIA) and University of Chinese Academy of Sciences (UCAS) and Centre for Artificial Intelligence and Robotics HKISI_CAS

As it is empirically observed that Vision Transformers (ViTs) are quite insensitive to the order of input tokens, the need for an appropriate self-supervised pretext task that enhances the location awareness of ViTs is becoming evident. To address this, we present DropPos, a novel pretext task designed to reconstruct Dropped Positions. The formulation of DropPos is simple: we first drop a large random subset of positional embeddings and then the model classifies the actual position for each non-overlapping patch among all possible positions solely based on their visual appearance. To avoid trivial solutions, we increase the difficulty of this task by keeping only a subset of patches visible. Additionally, considering there may be different patches with similar visual appearances, we propose position smoothing and attentive reconstruction strategies to relax this classification problem, since it is not necessary to reconstruct their exact positions in these cases. Empirical evaluations of DropPos show strong capabilities. DropPos outperforms supervised pre-training and achieves competitive results compared with state-of-the-art self-supervised alternatives on a wide range of downstream benchmarks. This suggests that explicitly encouraging spatial reasoning abilities, as DropPos does, indeed contributes to the improved location awareness of ViTs. The code is publicly available at https://***/Haochen-Wang409/DropPos.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MVBoost: Boost 3D Reconstruction with Multi-View Refinement

arXiv

引用

arXiv 2024年

作者： Liu, Xiangyu Zhang, Xiaomei Ma, Zhiyuan Lei, Zhen Zhu, Xiangyu State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China The Hong Kong Polytechnic University Hong Kong Center for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong

Recent advancements in 3D object reconstruction have been remarkable, yet most current 3D models rely heavily on existing 3D datasets. The scarcity of diverse 3D datasets results in limited generalization capabilities of 3D reconstruction models. In this paper, we propose a novel framework for boosting 3D reconstruction with multi-view refinement (MVBoost) by generating pseudo-GT data. The key of MVBoost is combining the advantages of the high accuracy of the multi-view generation model and the consistency of the 3D reconstruction model to create a reliable data source. Specifically, given a single-view input image, we employ a multi-view diffusion model to generate multiple views, followed by a large 3D reconstruction model to produce consistent 3D data. MVBoost then adaptively refines these multi-view images, rendered from the consistent 3D data, to build a large-scale multi-view dataset for training a feed-forward 3D reconstruction model. Additionally, the input view optimization is designed to optimize the corresponding viewpoints based on the user’s input image, ensuring that the most important viewpoint is accurately tailored to the user’s needs. Extensive evaluations demonstrate that our method achieves superior reconstruction results and robust generalization compared to prior works. Copyright © 2024, The Authors. All rights reserved.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

Towards Non-Exemplar Semi-Supervised Class-Incremental Learning

arXiv

引用

arXiv 2024年

作者： Liu, Wenzhuo Zhu, Fei Liu, Cheng-Lin The University of Chinese Academy of Sciences Beijing China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences 95 Zhongguancun East Road Beijing100190 China The Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science and Innovation Chinese Academy of Sciences 999077 Hong Kong

Deep neural networks perform remarkably well in close-world scenarios. However, novel classes emerged continually in real applications, making it necessary to learn incrementally. Class-incremental learning (CIL) aims to gradually recognize new classes while maintaining the discriminability of old ones. Existing CIL methods have two limitations: a heavy reliance on preserving old data for forgetting mitigation and the need for vast labeled data for knowledge adaptation. To overcome these issues, we propose a non-exemplar semi-supervised CIL framework with contrastive learning and semi-supervised incremental prototype classifier (Semi-IPC). On the one hand, contrastive learning helps the model learn rich representations, easing the trade-off between learning representations of new classes and forgetting that of old classes. On the other hand, Semi-IPC learns a prototype for each class with unsupervised regularization, enabling the model to incrementally learn from partially labeled new data while maintaining the knowledge of old classes. Experiments on benchmark datasets demonstrate the strong performance of our method: without storing any old samples and only using less than 1% of labels, Semi-IPC outperforms advanced exemplar-based methods. We hope our work offers new insights for future CIL research. The code will be made publicly available. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Design and preliminary testing of a piezoelectric-based sole energy harvester

Design and preliminary testing of a piezoelectric-based sole...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Wang, Yidi Zhao, Xuan Shi, Qiuyu Liao, Haisu Wu, Xinyu Gao, Fei Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen518055 China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Shatin999077 Hong Kong

ISBN: (纸本)9781665481090

Harvesting energy from the human body to replenish existing energy sources is receiving substantial attention. Recently scientists have been focusing on harvesting biomechanical energy from human feet during walking. This paper develops a piezoelectric-based sole energy harvester that is designed to be worn on the bottom of shoes to harvest energy, thus powering wearable electronic devices. Specifically, a cam with piezoelectric(PZT) stacks is mounted on the heel to scavenge energy during the heel strike. The cam can change the input's direction from the vertical direction to the horizontal direction. In addition, the output power of this part can be optimized or improved by generating a specified cam profile. A bimorph piezoelectric plate is installed on the forefoot to convert the toes' bending deformation into electricity. Herein, piezoelectric Macro Fiber Composites (MFC) are employed to capture the large deformation. Preliminary testing on a healthy subject is conducted to validate this design. The average power output of the harvester is 8.83 m W. © 2022 IEEE.

关键词： Cams

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：