检索结果-内蒙古大学图书馆

A Point-to-distribution Degeneracy Detection Factor for LiDAR SLAM using Local Geometric Models

学校读者我要写书评

暂无评论

A Point-to-distribution Degeneracy Detection Factor for LiDA...

IEEE International Conference on robotics and Automation (ICRA)

作者： Sehua Ji Weinan Chen Zerong Su Yisheng Guan Jiehao Li Hong Zhang Haifei Zhu Biomimetic and Intelligent Robotics Lab (BIRL) School of Electromechanical Engineer Guangdong University of Technology Guangzhou China JT-Innovation (Guangdong) Intelligent Technology Co. Ltd. Guangdong Key Laboratory of Modern Control Technology Institute of Intelligent Manufacturing Guangdong Academy of Sciences Guangzhou China College of Engineering South China Agricultural University China Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Limited by the working principles, LiDAR-SLAM systems suffer from the degeneration phenomenon in environments such as long corridors and tunnels, due to the lack of sufficient geometric features for frame-to-frame matching. The accuracy and sensitivity of existing degeneracy detection methods need to be further improved. In this paper, we propose a novel method for degeneracy detection using local geometric models based on point-to-distribution matching. To obtain an accurate description of local geometric models, an adaptive adjustment of voxel segmentation according to the point cloud distribution and density is designed. The codes of the proposed method is open-source and available at https://***/jisehua/***. Experiments with public datasets and self-build robots were conducted to evaluate the methods. The results exhibit that our proposed method achieves higher accuracy than the other existing approaches. Applying our proposed method is beneficial for improving the robustness of the LiDAR-SLAM systems.

关键词： Point cloud compression Accuracy Simultaneous localization and mapping Sensitivity Laser radar Geometric modeling Noise

Efficient Image Super-Resolution using Vast-Receptive-Field Attention

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhou, Lin Cai, Haoming Gu, Jinjin Li, Zheyuan Liu, Yingqi Chen, Xiangyu 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 Shanghai AI Laboratory Shanghai China The University of Sydney Australia University of Macau China

The attention mechanism plays a pivotal role in designing advanced super-resolution (SR) networks. In this work, we design an efficient SR network by improving the attention mechanism. We start from a simple pixel attention module and gradually modify it to achieve better super-resolution performance with reduced parameters. The specific approaches include: (1) increasing the receptive field of the attention branch, (2) replacing large dense convolution kernels with depth-wise separable convolutions, and (3) introducing pixel normalization. These approaches paint a clear evolutionary roadmap for the design of attention mechanisms. Based on these observations, we propose VapSR, the VAst-receptive-field Pixel attention network. Experiments demonstrate the superior performance of VapSR. VapSR outperforms the present lightweight networks with even fewer parameters. And the light version of VapSR can use only 21.68% and 28.18% parameters of IMDB and RFDN to achieve similar performances to those networks. The code and models are available at https://***/zhoumumu/VapSR. Copyright © 2022, The Authors. All rights reserved.

关键词： Pixels

CSSL-MHTR: Continual Self-Supervised Learning for Scalable Multi-script Handwritten Text Recognition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Dhiaf, Marwa Souibgui, Mohamed Ali Wang, Kai Liu, Yuyang Kessentini, Yousri Fornés, Alicia Rouhou, Ahmed Cheikh InstaDeep United Kingdom Computer Vision Center UAB Spain Digital Research Center of Sfax SM@RTS Tunisia State Key Laboratory of Robotics China Shenyang Institute of Automation Chinese Academy of Sciences China

Self-supervised learning has recently emerged as a strong alternative in document analysis. These approaches are now capable of learning high-quality image representations and overcoming the limitations of supervised methods, which require a large amount of labeled data. However, these methods are unable to capture new knowledge in an incremental fashion, i.e. when data is presented to the model sequentially, which is closer to the realistic scenario. In this paper, we explore the potential of continual self-supervised learning to alleviate the catastrophic forgetting problem in handwritten text recognition, as an example of sequence recognition. Our method consists in adding intermediate layers called adapters for each task, and efficiently distilling knowledge from the previous model while learning the current task. Our proposed framework is efficient in both computation and memory complexity. To demonstrate its effectiveness, we evaluate our method by transferring the learned model to diverse text recognition downstream tasks, including Latin and non-Latin scripts. As far as we know, this is the first application of continual self-supervised learning for handwritten text recognition. We attain state-of-the-art performance in English, Italian, and Russian, whilst adding only a few parameters per task. The code and trained models will be publicly available1 © 2023, CC BY.

关键词： Supervised learning

Dual-Teacher: Integrating Intra-domain and Inter-domain Teachers for Annotation-efficient Cardiac Segmentation

学校读者我要写书评

暂无评论

arXiv 2020年

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

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. Copyright © 2020, The Authors. All rights reserved.

关键词： Large dataset

UniTSFace: Unified Threshold Integrated Sample-to-Sample Loss for Face Recognition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Qiufu Jia, Xi Zhou, Jiancan Shen, Linlin Duan, Jinming National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Computer Vision Institute Shenzhen University China School of Computer Science University of Birmingham United Kingdom Aqara Lumi United Technology Co. Ltd China Alan Turing Institute United Kingdom SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Sample-to-class-based face recognition models can not fully explore the cross-sample relationship among large amounts of facial images, while sample-to-sample-based models require sophisticated pairing processes for training. Furthermore, neither method satisfies the requirements of real-world face verification applications, which expect a unified threshold separating positive from negative facial pairs. In this paper, we propose a unified threshold integrated sample-to-sample based loss (USS loss), which features an explicit unified threshold for distinguishing positive from negative pairs. Inspired by our USS loss, we also derive the sample-to-sample based softmax and BCE losses, and discuss their relationship. Extensive evaluation on multiple benchmark datasets, including MFR, IJB-C, LFW, CFP-FP, AgeDB, and MegaFace, demonstrates that the proposed USS loss is highly efficient and can work seamlessly with sample-to-class-based losses. The embedded loss (USS and sample-to-class Softmax loss) overcomes the pitfalls of previous approaches and the trained facial model UniTSFace exhibits exceptional performance, outperforming state-of-the-art methods, such as CosFace, ArcFace, VPL, AnchorFace, and UNPG. Our code is available at https://***/CVI-SZU/UniTSFace. © 2023, CC BY.

关键词： Face recognition

Age-Group Classification of Facial Images

学校读者我要写书评

暂无评论

Age-Group Classification of Facial Images

International Conference on Machine Learning and Applications (ICMLA)

作者： Li Liu Jianming Liu Jun Cheng Shenzhen Institutes of Advanced Technolozv Chinese Academv of Science Computer Science and Engineering Department School of Guilin University of Electronic Technology Guilin China Guangdong Provincial Key Laboratory of Robotics and Intelligent System

This paper presents the age-group classification based on facial images. We perform age-group classification by dividing ages into five age groups according to the incremental regulation of age. Features are extracted from face images through Active Appearance Model (AAM), which describe the shape and gray value variation of face images. Principle Component Analysis (PCA) is adopted to reduce the dimensions and Support Vector Machine (SVM) classifier with Gaussian Radian Basis Function (RBF) kernel is trained. Experimental results demonstrate that AAM can improve the performance of age estimation.

关键词： Machine learning

Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection

学校读者我要写书评

暂无评论

Augmented Box Replay: Overcoming Foreground Shift for Increm...

International Conference on computer vision (ICCV)

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

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 .

关键词：

MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling with Informative-Preserved Reconstruction and Self-Distilled Consistency

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xu, Mingye Xu, Mutian He, Tong Ouyang, Wanli Wang, Yali Han, Xiaoguang Qiao, Yu The Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China SSE CUHKSZ China University of Chinese Academy of Sciences China Shanghai Artificial Intelligence Laboratory China FNii CUHKSZ China

Masked Modeling (MM) has demonstrated widespread success in various vision challenges, by reconstructing masked visual patches. Yet, applying MM for large-scale 3D scenes remains an open problem due to the data sparsity and scene complexity. The conventional random masking paradigm used in 2D images often causes a high risk of ambiguity when recovering the masked region of 3D scenes. To this end, we propose a novel informative-preserved reconstruction, which explores local statistics to discover and preserve the representative structured points, effectively enhancing the pretext masking task for 3D scene understanding. Integrated with a progressive reconstruction manner, our method can concentrate on modeling regional geometry and enjoy less ambiguity for masked reconstruction. Besides, such scenes with progressive masking ratios can also serve to self-distill their intrinsic spatial consistency, requiring to learn the consistent representations from unmasked areas. By elegantly combining informative-preserved reconstruction on masked areas and consistency self-distillation from unmasked areas, a unified framework called MM-3DScene is yielded. We conduct comprehensive experiments on a host of downstream tasks. The consistent improvement (e.g., +6.1% mAP@0.5 on object detection and +2.2% mIoU on semantic segmentation) demonstrates the superiority of our approach. © 2022, CC BY-NC-SA.

关键词： Distillation

Pseudo-label Guided Cross-video Pixel Contrast for Robotic Surgical Scene Segmentation with Limited Annotations

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yu, Yang Zhao, Zixu Jin, Yueming Chen, Guangyong Dou, Qi Heng, Pheng-Ann The 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 Chinese Academy of Sciences Shenzhen China The Department of Computer Science University College London United Kingdom Zhejiang Lab China

Surgical scene segmentation is fundamentally crucial for prompting cognitive assistance in robotic surgery. However, pixel-wise annotating surgical video in a frame-by-frame manner is expensive and time consuming. To greatly reduce the labeling burden, in this work, we study semi-supervised scene segmentation from robotic surgical video, which is practically essential yet rarely explored before. We consider a clinically suitable annotation situation under the equidistant sampling. We then propose PGV-CL, a novel pseudo-label guided cross-video contrast learning method to boost scene segmentation. It effectively leverages unlabeled data for a trusty and global model regularization that produces more discriminative feature representation. Concretely, for trusty representation learning, we propose to incorporate pseudo labels to instruct the pair selection, obtaining more reliable representation pairs for pixel contrast. Moreover, we expand the representation learning space from previous image-level to cross-video, which can capture the global semantics to benefit the learning process. We extensively evaluate our method on a public robotic surgery dataset EndoVis18 and a public cataract dataset CaDIS. Experimental results demonstrate the effectiveness of our method, consistently outperforming the state-of-the-art semi-supervised methods under different labeling ratios, and even surpassing fully supervised training on EndoVis18 with 10.1% labeling. Our code is available at https://***/yangyu-cuhk/PGVCL. Copyright © 2022, The Authors. All rights reserved.

关键词： Robotic surgery