检索结果-内蒙古大学图书馆

Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Yang Chen, Chen Wang, Can King, Xulin Liu, Mengyuan College of Computer Science Sichuan University China Center for Research in Computer Vision University of Central Florida United States Laboratory on Multimedia Information Processing The Department of Computer Science Kiel University Hangzhou Linxrobot Company China Hangzhou GOTHEN Technology Co. Ltd China Key Laboratory of Machine Perception Shenzhen Graduate School Peking University China

Masked Autoencoders (MAE) have demonstrated promising performance in self-supervised learning for both 2D and 3D computer vision. Nevertheless, existing MAE-based methods still have certain drawbacks. Firstly, the functional decoupling between the encoder and decoder is incomplete, which limits the encoder’s representation learning ability. Secondly, downstream tasks solely utilize the encoder, failing to fully leverage the knowledge acquired through the encoder-decoder architecture in the pre-text task. In this paper, we propose Point Regress AutoEncoder (Point-RAE), a new scheme for regressive autoencoders for point cloud self-supervised learning. The proposed method decouples functions between the decoder and the encoder by introducing a mask regressor, which predicts the masked patch representation from the visible patch representation encoded by the encoder and the decoder reconstructs the target from the predicted masked patch representation. By doing so, we minimize the impact of decoder updates on the representation space of the encoder. Moreover, we introduce an alignment constraint to ensure that the representations for masked patches, predicted from the encoded representations of visible patches, are aligned with the masked patch presentations computed from the encoder. To make full use of the knowledge learned in the pre-training stage, we design a new finetune mode for the proposed Point-RAE. Extensive experiments demonstrate that our approach is efficient during pre-training and generalizes well on various downstream tasks. Specifically, our pretrained models achieve a high accuracy of 90.28% on the ScanObjectNN hardest split and 94.1% accuracy on ModelNet40, surpassing all the other self-supervised learning methods. Our code and pretrained model are public available at: https://***/liuyyy111/ Point-RAE. Copyright © 2023, The Authors. All rights reserved.

关键词： Supervised learning

Advancing Virtual Reality Interaction: A Ring-Shaped Controller and Pose Tracking

学校读者我要写书评

暂无评论

Advancing Virtual Reality Interaction: A Ring-Shaped Control...

IEEE International Conference on robotics and Automation (ICRA)

作者： Zhuqing Zhang Dongxuan Li Jiayao Ma Yijia He Pan Ji Rong Xiong Hongdong Li Yue Wang State Key Laboratory of Industrial Control Technology and Institute of Cyber-Systems and Control Zhejiang University Zhejiang China Tencent Holdings Tencent XR Vision Labs Shenzhen China College of Engineering and Computer Science Australian National University Canberra

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Ensuring robust tracking of controllers’ movement is critical for human-robot interaction in virtual reality (VR) scenarios. This paper proposes a robust tracking algorithm based on a novel wearable ring-shaped controller equipped with an inertial measurement unit (IMU) and a light-emitting diode (LED). This novel controller design allows users to free up their hands for more immersive experiences. To track the controller’s motion accurately and robustly, we resort to various forms of visual measurements, including 6 DoF and 5 DoF pose measurements from hand gesture detection, as well as 3 DoF position measurement and 2 DoF image measurement derived from the LED. We theoretically analyze the performances of these observation models and propose an optimal observation model combination scheme. Moreover, the necessity and rationale of online estimating system gravity are illustrated. The effectiveness of our tracking method is validated through extensive experiments.

关键词： Solid modeling Analytical models Visualization Measurement units Tracking Virtual reality Inertial navigation

Efficient Single-Image Depth Estimation on Mobile Devices, Mobile AI & AIM 2022 Challenge: Report 17th

学校读者我要写书评

暂无评论

Efficient Single-Image Depth Estimation on Mobile Devices, ...

17th European Conference on computer vision, ECCV 2022

作者： Ignatov, Andrey Malivenko, Grigory Timofte, Radu Treszczotko, Lukasz Chang, Xin Ksiazek, Piotr Lopuszynski, Michal Pioro, Maciej Rudnicki, Rafal Smyl, Maciej Ma, Yujie Li, Zhenyu Chen, Zehui Xu, Jialei Liu, Xianming Jiang, Junjun Shi, XueChao Xu, Difan Li, Yanan Wang, Xiaotao Lei, Lei Zhang, Ziyu Wang, Yicheng Huang, Zilong Luo, Guozhong Yu, Gang Fu, Bin Li, Jiaqi Wang, Yiran Huang, Zihao Cao, Zhiguo Conde, Marcos V. Sapozhnikov, Denis Lee, Byeong Hyun Park, Dongwon Hong, Seongmin Lee, Joonhee Lee, Seunggyu Chun, Se Young Computer Vision Lab ETH Zürich Zürich Switzerland AI Witchlabs Zollikerberg Switzerland University of Wuerzburg Wuerzburg Germany TCL Research Europe Warsaw Poland Harbin Institute of Technology Harbin China Xiaomi Inc. Beijing China Tencent GY-Lab Shenzhen China National Key Laboratory of Science and Technology on Multi-Spectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of

ISBN: (纸本)9783031250651

Various depth estimation models are now widely used on many mobile and IoT devices for image segmentation, bokeh effect rendering, object tracking and many other mobile tasks. Thus, it is very crucial to have efficient and accurate depth estimation models that can run fast on low-power mobile chipsets. In this Mobile AI challenge, the target was to develop deep learning-based single image depth estimation solutions that can show a real-time performance on IoT platforms and smartphones. For this, the participants used a large-scale RGB-to-depth dataset that was collected with the ZED stereo camera capable to generated depth maps for objects located at up to 50 m. The runtime of all models was evaluated on the Raspberry Pi 4 platform, where the developed solutions were able to generate VGA resolution depth maps at up to 27 FPS while achieving high fidelity results. All models developed in the challenge are also compatible with any Android or Linux-based mobile devices, their detailed description is provided in this paper. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Image segmentation

UniFormer: Unifying Convolution and Self-attention for Visual Recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Kunchang Wang, Yali Zhang, Junhao Gao, Peng Song, Guanglu Liu, Yu Li, Hongsheng Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China University of Chinese Academy of Sciences Beijing100049 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China National University of Singapore Singapore Shanghai Artificial Intelligence Laboratory China SenseTime Research China The Chinese University of Hong Kong Hong Kong

It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolution neural networks (CNNs) and vision transformers (ViTs) have been two dominant frameworks in the past few years. Though CNNs can efficiently decrease local redundancy by convolution within a small neighborhood, the limited receptive field makes it hard to capture global dependency. Alternatively, ViTs can effectively capture long-range dependency via self-attention, while blind similarity comparisons among all the tokens lead to high redundancy. To resolve these problems, we propose a novel Unified transFormer (UniFormer), which can seamlessly integrate the merits of convolution and self-attention in a concise transformer format. Different from the typical transformer blocks, the relation aggregators in our UniFormer block are equipped with local and global token affinity respectively in shallow and deep layers, allowing tackling both redundancy and dependency for efficient and effective representation learning. Finally, we flexibly stack our blocks into a new powerful backbone, and adopt it for various vision tasks from image to video domain, from classification to dense prediction. Without any extra training data, our UniFormer achieves 86.3 top-1 accuracy on ImageNet-1K classification task. With only ImageNet-1K pre-training, it can simply achieve state-of-the-art performance in a broad range of downstream tasks. It obtains 82.9/84.8 top-1 accuracy on Kinetics-400/600, 60.9/71.2 top-1 accuracy on Something-Something V1/V2 video classification tasks, 53.8 box AP and 46.4 mask AP on COCO object detection task, 50.8 mIoU on ADE20K semantic segmentation task, and 77.4 AP on COCO pose estimation task. Moreover, we build an efficient UniFormer with a concise hourglass design of token shrinking and recovering, which achieves 2-4× higher throughput than the recent lightweight models. Code is av

关键词： Convolution

Bidirectional Search Strategy for Incremental Search-based Path Planning

学校读者我要写书评

暂无评论

Bidirectional Search Strategy for Incremental Search-based P...

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Chenming Li Han Ma Jiankun Wang Max Q.-H. Meng Department of Electronic Engineering The Chinese University of Hong Kong Shatin N.T. Hong Kong SAR China Department of Electronic and Electrical Engineering Shenzhen Key Laboratory of Robotics Perception and Intelligence Southern University of Science and Technology Shenzhen China Jiaxing Research Institute Southern University of Science and Technology Jiaxing China Department of Electronic and Electrical Engineering Shenzhen Key Laboratory of Robotics Per-ception and Intelligence Southern University of Science and Technology Shenzhen China Emeritus in the Department of Electronic Engineering The Chinese University of Hong Kong in Hong Kong Department of Electrical and Computer Engineering University of Alberta in Canada

Planning a collision-free path efficiently among obstacles is crucial in robotics. Conventional one-shot unidirectional path planning algorithms work well in the static environment, but cannot respond to the environment changes timely in the dynamic environment. To tackle this issue and improve the search efficiency, we propose a bidirectional incremental search method, Bidirectional Lifelong Planning A* (BLPA*), which searches in the forward and backward directions and performs incremental search bidirectionally when the environment changes. Furthermore, inspired by the robot perception range limitation and BLPA*, we propose the fractional bidirectional D* Lite (fBD* Lite(d p )), which constraints the forward search to the robot perception range and uses the backward search to expand the rest area. Our simulation results demonstrate BLPA* and mD* Lite(d p ) can achieve superior performance in the dynamic environment. It reveals that the bidirectional incremental search strategy can be a general and efficient technique for graph-search-based robot path planning methods.

关键词：

Identifiability Analysis of Noise Covariances for LTI Stochastic Systems with Unknown Inputs

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kong, He Sukkarieh, Salah Arnold, Travis J. Chen, Tianshi Mu, Biqiang Zheng, Wei Xing Shenzhen518055 China Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities SUSTech Shenzhen518055 China Sydney Institute for Robotics and Intelligent Systems The University of Sydney NSW2006 Australia Madison WI53704 United States School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen518172 China Key Laboratory of Systems and Control Institute of Systems Science Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China School of Computer Data and Mathematical Sciences Western Sydney University SydneyNSW2751 Australia

Most existing works on optimal filtering of linear time-invariant (LTI) stochastic systems with arbitrary unknown inputs assume perfect knowledge of the covariances of the noises in the filter design. This is impractical and raises the question of whether and under what conditions one can identify the process and measurement noise covariances (denoted as Q and R, respectively) of systems with unknown inputs. This paper considers the identifiability of Q/R using the correlation-based measurement difference approach. More specifically, we establish (i) necessary conditions under which Q and R can be uniquely jointly identified;(ii) necessary and sufficient conditions under which Q can be uniquely identified, when R is known;(iii) necessary conditions under which R can be uniquely identified, when Q is known. It will also be shown that for achieving the results mentioned above, the measurement difference approach requires some decoupling conditions for constructing a stationary time series, which are proved to be sufficient for the well-known strong detectability requirements established by Hautus. © 2022, CC BY.

关键词： Stochastic systems

Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Yuyang Cong, Yang Goswami, Dipam Liu, Xialei van de Weijer, Joost State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences China University of Chinese Academy of Sciences China South China University of Technology China Computer Vision Center Barcelona Spain VCIP CS Nankai University China Department of Computer Science Universitat Autònoma de Barcelona Spain

In incremental learning, replaying stored samples from previous tasks together with current task samples is one of the most efficient approaches to address catastrophic forgetting. However, unlike incremental classification, image replay has not been successfully applied to incremental object detection (IOD). In this paper, we identify the overlooked problem of foreground shift as the main reason for this. Foreground shift only occurs when replaying images of previous tasks and refers to the fact that their background might contain foreground objects of the current task. To overcome this problem, a novel and efficient Augmented Box Replay (ABR) method is developed that only stores and replays foreground objects and thereby circumvents the foreground shift problem. In addition, we propose an innovative Attentive RoI Distillation loss that uses spatial attention from region-of-interest (RoI) features to constrain current model to focus on the most important information from old model. ABR significantly reduces forgetting of previous classes while maintaining high plasticity in current classes. Moreover, it considerably reduces the storage requirements when compared to standard image replay. Comprehensive experiments on Pascal-VOC and COCO datasets support the state-of-the-art performance of our model 1 © 2023, CC BY.

关键词： Object detection

RepMode: Learning to Re-parameterize Diverse Experts for Subcellular Structure Prediction

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhou, Donghao Gu, Chunbin Xu, Junde Liu, Furui Wang, Qiong Chen, Guangyong Heng, Pheng-Ann Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China The Chinese University of Hong Kong Hong Kong Zhejiang Lab China

In biological research, fluorescence staining is a key technique to reveal the locations and morphology of subcellular structures. However, it is slow, expensive, and harmful to cells. In this paper, we model it as a deep learning task termed subcellular structure prediction (SSP), aiming to predict the 3D fluorescent images of multiple subcellular structures from a 3D transmitted-light image. Unfortunately, due to the limitations of current biotechnology, each image is partially labeled in SSP. Besides, naturally, subcellular structures vary considerably in size, which causes the multi-scale issue of SSP. To overcome these challenges, we propose Re-parameterizing Mixture-of-Diverse-Experts (RepMode), a network that dynamically organizes its parameters with task-aware priors to handle specified single-label prediction tasks. In RepMode, the Mixture-of-Diverse-Experts (MoDE) block is designed to learn the generalized parameters for all tasks, and gating re-parameterization (GatRep) is performed to generate the specialized parameters for each task, by which RepMode can maintain a compact practical topology exactly like a plain network, and meanwhile achieves a powerful theoretical topology. Comprehensive experiments show that RepMode can achieve state-of-the-art overall performance in SSP. Copyright © 2022, The Authors. All rights reserved.

关键词： Forecasting

LHNN: Lattice Hypergraph Neural Network for VLSI Congestion Prediction

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Bowen Shen, Guibao Li, Dong Hao, Jianye Liu, Wulong Huang, Yu Wu, Hongzhong Lin, Yibo Chen, Guangyong Heng, Pheng Ann Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology China Huawei Noah’s Ark Lab Hong Kong Huawei Hisilicon China Department of Computer Science Peking University China

Precise congestion prediction from a placement solution plays a crucial role in circuit placement. This work proposes the lattice hypergraph (LH-graph), a novel graph formulation for circuits, which preserves netlist data during the whole learning process, and enables the congestion information propagated geometrically and topologically. Base on the formulation, we further developed a heterogeneous graph neural network architecture LHNN, jointing the routing demand regression to support the congestion spot classification. LHNN constantly achieves more than 35% improvements compared with U-nets and Pix2Pix on the F1 score. We expect our work shall highlight essential procedures using machine learning for congestion prediction. Copyright © 2022, The Authors. All rights reserved.

关键词： VLSI circuits